Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 977 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7307. Min Range: -3.7307
Max Act: 3.7307. Min Act: -0.1700
Data Index: 930862 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7307. Min Range: -3.7307
Max Act: 3.5899. Min Act: -0.1700
Data Index: 49580 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7307. Min Range: -3.7307
Max Act: 3.5116. Min Act: -0.1700
Data Index: 3339079 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7307. Min Range: -3.7307
Max Act: 3.5116. Min Act: -0.1700
Data Index: 3892637 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7307. Min Range: -3.7307
Max Act: 3.5116. Min Act: -0.1700
Data Index: 7110119 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7307. Min Range: -3.7307
Max Act: 3.5272. Min Act: -0.1700
Data Index: 1362205 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7307. Min Range: -3.7307
Max Act: 3.4959. Min Act: -0.1700
Data Index: 3541720 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7307. Min Range: -3.7307
Max Act: 3.4959. Min Act: -0.1700
Data Index: 2692583 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7307. Min Range: -3.7307
Max Act: 3.4646. Min Act: -0.1700
Data Index: 1597540 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7307. Min Range: -3.7307
Max Act: 3.4803. Min Act: -0.0219
Data Index: 5378624 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7307. Min Range: -3.7307
Max Act: 3.4646. Min Act: -0.1700
Data Index: 4343083 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7307. Min Range: -3.7307
Max Act: 3.4646. Min Act: -0.1700
Data Index: 6388012 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7307. Min Range: -3.7307
Max Act: 3.4646. Min Act: -0.1700
Data Index: 7891015 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7307. Min Range: -3.7307
Max Act: 3.4646. Min Act: -0.1700
Data Index: 6190941 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7307. Min Range: -3.7307
Max Act: 3.4176. Min Act: -0.1700
Data Index: 7732539 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7307. Min Range: -3.7307
Max Act: 3.4176. Min Act: -0.1700
Data Index: 7899416 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7307. Min Range: -3.7307
Max Act: 3.4333. Min Act: -0.1686
Data Index: 6792975 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7307. Min Range: -3.7307
Max Act: 3.4333. Min Act: -0.1700
Data Index: 5639277 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7307. Min Range: -3.7307
Max Act: 3.4489. Min Act: -0.1700
Data Index: 208964 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7307. Min Range: -3.7307
Max Act: 3.4333. Min Act: -0.1700
Data Index: 6478537 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19