Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3239 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1380. Min Range: -7.1380
Max Act: 7.1380. Min Act: -0.1700
Data Index: 32423 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1380. Min Range: -7.1380
Max Act: 7.0442. Min Act: -0.1700
Data Index: 4414939 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1380. Min Range: -7.1380
Max Act: 6.9817. Min Act: -0.1700
Data Index: 1987128 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1380. Min Range: -7.1380
Max Act: 6.9192. Min Act: -0.1700
Data Index: 4738871 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1380. Min Range: -7.1380
Max Act: 6.9192. Min Act: -0.1700
Data Index: 2060410 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1380. Min Range: -7.1380
Max Act: 6.8880. Min Act: -0.1700
Data Index: 4785550 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1380. Min Range: -7.1380
Max Act: 6.8880. Min Act: -0.1700
Data Index: 3781159 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1380. Min Range: -7.1380
Max Act: 6.8567. Min Act: -0.1700
Data Index: 3197445 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1380. Min Range: -7.1380
Max Act: 6.7942. Min Act: -0.1700
Data Index: 1133837 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1380. Min Range: -7.1380
Max Act: 6.7630. Min Act: -0.1700
Data Index: 6973262 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1380. Min Range: -7.1380
Max Act: 6.7630. Min Act: -0.1700
Data Index: 4036147 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1380. Min Range: -7.1380
Max Act: 6.7317. Min Act: -0.1700
Data Index: 342844 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1380. Min Range: -7.1380
Max Act: 6.7317. Min Act: -0.1700
Data Index: 4785551 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1380. Min Range: -7.1380
Max Act: 6.7317. Min Act: -0.1700
Data Index: 3981205 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1380. Min Range: -7.1380
Max Act: 6.7317. Min Act: -0.1700
Data Index: 3879100 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1380. Min Range: -7.1380
Max Act: 6.7317. Min Act: -0.1700
Data Index: 6866321 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1380. Min Range: -7.1380
Max Act: 6.7005. Min Act: -0.1700
Data Index: 4966727 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1380. Min Range: -7.1380
Max Act: 6.7005. Min Act: -0.1700
Data Index: 680771 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1380. Min Range: -7.1380
Max Act: 6.7005. Min Act: -0.1700
Data Index: 6443242 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1380. Min Range: -7.1380
Max Act: 6.7005. Min Act: -0.1700
Data Index: 362028 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19