Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3855 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9291. Min Range: -6.9291
Max Act: 6.9291. Min Act: -0.1700
Data Index: 8038652 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9291. Min Range: -6.9291
Max Act: 6.7728. Min Act: -0.1700
Data Index: 3847982 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9291. Min Range: -6.9291
Max Act: 6.7103. Min Act: -0.1700
Data Index: 3162697 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9291. Min Range: -6.9291
Max Act: 6.5853. Min Act: -0.1700
Data Index: 3099612 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9291. Min Range: -6.9291
Max Act: 6.6166. Min Act: -0.1700
Data Index: 2202405 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9291. Min Range: -6.9291
Max Act: 6.5228. Min Act: -0.1700
Data Index: 1495852 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9291. Min Range: -6.9291
Max Act: 6.5228. Min Act: -0.1700
Data Index: 1577883 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9291. Min Range: -6.9291
Max Act: 6.4916. Min Act: -0.1700
Data Index: 387821 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9291. Min Range: -6.9291
Max Act: 6.4291. Min Act: -0.1700
Data Index: 5047337 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9291. Min Range: -6.9291
Max Act: 6.3978. Min Act: -0.1700
Data Index: 7078110 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9291. Min Range: -6.9291
Max Act: 6.3978. Min Act: -0.1700
Data Index: 4950590 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9291. Min Range: -6.9291
Max Act: 6.4291. Min Act: -0.1700
Data Index: 1605896 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9291. Min Range: -6.9291
Max Act: 6.4291. Min Act: -0.1700
Data Index: 4666953 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9291. Min Range: -6.9291
Max Act: 6.4291. Min Act: -0.1700
Data Index: 2207708 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9291. Min Range: -6.9291
Max Act: 6.4291. Min Act: -0.1700
Data Index: 5457878 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9291. Min Range: -6.9291
Max Act: 6.3666. Min Act: -0.1700
Data Index: 888853 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9291. Min Range: -6.9291
Max Act: 6.3978. Min Act: -0.1700
Data Index: 3498662 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9291. Min Range: -6.9291
Max Act: 6.3353. Min Act: -0.1700
Data Index: 5955287 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9291. Min Range: -6.9291
Max Act: 6.3666. Min Act: -0.1700
Data Index: 4351740 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9291. Min Range: -6.9291
Max Act: 6.3978. Min Act: -0.1700
Data Index: 8038657 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19