We haven’t yet got a precise formulation of “anomalousness” or “glitchiness”—it’s still an intuitive concept. I’ve run some experiments over the entire token set, prompting a large number of times and measuring the proportion of times GPT-3 (or GPT-J) correctly reproduces the token string. This is a starting point, but there seem to be two separate things going on with (1) GPT’s inability to repeat back “headless” tokens like “ertain”, “acebook” or “ortunately” and (2) its inability to repeat back the “true glitch tokens” like ” SolidGoldMagikarp” and ” petertodd”.
“GoldMagikarp” did show up in our original list of anomalous tokens, btw.
Yes, I realised that this was a downfall of n.c.p. It’s helpful for shorter rollouts, but once they get longer they can get into a kind of “probabilistic groove” which starts to unhelpfully inflate n.c.p. In mode collapse loops, n.c.p. tends to 1. So yeah, good observation.