“Anomalous”, “glitch”, or “unspeakable” tokens in an LLM are those that induce bizarre behavior or otherwise don’t behave like regular t

Anomalous Tokens in DeepSeek-V3 and r1 - by henry

submited by

Style Pass

2025-01-25 20:30:05

“Anomalous”, “glitch”, or “unspeakable” tokens in an LLM are those that induce bizarre behavior or otherwise don’t behave like regular text.

The SolidGoldMagikarp saga is pretty much essential context, as it documents the discovery of this phenomenon in GPT-2 and GPT-3.

But, as far as I was able to tell, nobody had yet attempted to search for these tokens in DeepSeek-V3, so I tried doing exactly that. Being a SOTA base model, open source, and an all-around strange LLM, it seemed like a perfect candidate for this.

This is a catalog of the glitch tokens I've found in DeepSeek after a day or so of experimentation, along with some preliminary observations about their behavior.

I searched for these tokens by first extracting the vocabulary from DeepSeek-V3's tokenizer, and then automatically testing every one of them for unusual behavior.

Note: For our purposes, r1 is effectively a layer on top of V3, and all anomalous tokens carry over. The distillations, on the other hand, are much more fundamentally similar to the pre-trains they're based on, so they will not be discussed.