Logan Riggs comments on You can remove GPT2’s LayerNorm by fine-tuning for an hour

[Logan Riggs]

And here’s the code to convert it to NNsight (Thanks Caden for writing this awhile ago!)

import torch
from transformers import GPT2LMHeadModel
from transformer_lens import HookedTransformer
from nnsight.models.UnifiedTransformer import UnifiedTransformer


model = GPT2LMHeadModel.from_pretrained("apollo-research/gpt2_noLN").to("cpu")

# Undo my hacky LayerNorm removal
for block in model.transformer.h:
    block.ln_1.weight.data = block.ln_1.weight.data / 1e6
    block.ln_1.eps = 1e-5
    block.ln_2.weight.data = block.ln_2.weight.data / 1e6
    block.ln_2.eps = 1e-5
model.transformer.ln_f.weight.data = model.transformer.ln_f.weight.data / 1e6
model.transformer.ln_f.eps = 1e-5

# Properly replace LayerNorms by Identities
def removeLN(transformer_lens_model):
    for i in range(len(transformer_lens_model.blocks)):
        transformer_lens_model.blocks[i].ln1 = torch.nn.Identity()
        transformer_lens_model.blocks[i].ln2 = torch.nn.Identity()
    transformer_lens_model.ln_final = torch.nn.Identity()

hooked_model = HookedTransformer.from_pretrained("gpt2", hf_model=model, fold_ln=True, center_unembed=False).to("cpu")
removeLN(hooked_model)

model_nnsight = UnifiedTransformer(model="gpt2", hf_model=model, fold_ln=True, center_unembed=False).to("cpu")
removeLN(model_nnsight)

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
prompt = torch.tensor([1,2,3,4], device=device)
logits = hooked_model(prompt)

with torch.no_grad(), model_nnsight.trace(prompt) as runner:
    logits2 = model_nnsight.unembed.output.save()
logits, cache = hooked_model.run_with_cache(prompt)
torch.allclose(logits, logits2)