Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2593 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3209. Min Range: -10.3209
Max Act: 10.3209. Min Act: -0.1700
Data Index: 7450939 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3209. Min Range: -10.3209
Max Act: 9.7584. Min Act: -0.1700
Data Index: 3168895 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3209. Min Range: -10.3209
Max Act: 9.2584. Min Act: -0.1700
Data Index: 3178454 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3209. Min Range: -10.3209
Max Act: 9.1959. Min Act: -0.1700
Data Index: 5604515 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3209. Min Range: -10.3209
Max Act: 9.1334. Min Act: -0.1700
Data Index: 2597542 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3209. Min Range: -10.3209
Max Act: 9.0709. Min Act: -0.1700
Data Index: 7090279 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3209. Min Range: -10.3209
Max Act: 9.0709. Min Act: -0.1700
Data Index: 4804827 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3209. Min Range: -10.3209
Max Act: 8.9459. Min Act: -0.1700
Data Index: 161375 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3209. Min Range: -10.3209
Max Act: 8.9459. Min Act: -0.1700
Data Index: 6236301 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3209. Min Range: -10.3209
Max Act: 8.9459. Min Act: -0.1700
Data Index: 6592301 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3209. Min Range: -10.3209
Max Act: 8.8834. Min Act: -0.1700
Data Index: 572544 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3209. Min Range: -10.3209
Max Act: 8.8834. Min Act: -0.1700
Data Index: 6492884 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3209. Min Range: -10.3209
Max Act: 8.8834. Min Act: -0.1700
Data Index: 387354 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3209. Min Range: -10.3209
Max Act: 8.7584. Min Act: -0.1700
Data Index: 7084741 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3209. Min Range: -10.3209
Max Act: 8.7584. Min Act: -0.1700
Data Index: 4167869 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3209. Min Range: -10.3209
Max Act: 8.7584. Min Act: -0.1700
Data Index: 1914519 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3209. Min Range: -10.3209
Max Act: 8.6959. Min Act: -0.1700
Data Index: 3423200 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3209. Min Range: -10.3209
Max Act: 8.6334. Min Act: -0.1700
Data Index: 3488415 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3209. Min Range: -10.3209
Max Act: 8.6334. Min Act: -0.1700
Data Index: 511668 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3209. Min Range: -10.3209
Max Act: 8.6334. Min Act: -0.1700
Data Index: 3915329 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19