What I found most fascinating is identifying neuron firing patterns corresponding to linguistic properties: e.g. groups of neurons that fire in response to verbs, or pronounds.
The figure above it, titled 'Explorable: Ten Activation Factors of XML' shows how neuron firing patterns in response to XML -- opening tags, closing tags, and even indentation.
It's still fresh, but I'm keen to see what other people uncover in their examinations (or what shortfalls/areas of improvement there are for such a method).
Scroll down to "Factorizing Activations of a Single Layer" in https://jalammar.github.io/explaining-transformers/ to see those.
The figure above it, titled 'Explorable: Ten Activation Factors of XML' shows how neuron firing patterns in response to XML -- opening tags, closing tags, and even indentation.
It's still fresh, but I'm keen to see what other people uncover in their examinations (or what shortfalls/areas of improvement there are for such a method).