Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 212 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.7319. Min Act: -0.1700
Data Index: 7443683 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.7319. Min Act: -0.1700
Data Index: 7095384 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.6067. Min Act: -0.1700
Data Index: 6260459 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.5441. Min Act: -0.1700
Data Index: 8738207 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.4971. Min Act: -0.1700
Data Index: 6483441 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.4658. Min Act: -0.1700
Data Index: 261443 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.4814. Min Act: -0.1700
Data Index: 2027916 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.4658. Min Act: -0.1700
Data Index: 3479760 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.4814. Min Act: -0.1700
Data Index: 7291032 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.4658. Min Act: -0.1700
Data Index: 5818103 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.4814. Min Act: -0.1700
Data Index: 6357870 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.4501. Min Act: -0.1700
Data Index: 1713677 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.4188. Min Act: -0.1700
Data Index: 2887509 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.4344. Min Act: -0.1700
Data Index: 7437777 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.4344. Min Act: -0.1700
Data Index: 6979776 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.4344. Min Act: -0.1700
Data Index: 4537236 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.4188. Min Act: -0.1700
Data Index: 5300880 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.4501. Min Act: -0.1700
Data Index: 6697623 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.4188. Min Act: -0.1700
Data Index: 2859168 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7319. Min Range: -3.7319
Max Act: 3.4344. Min Act: -0.1700
Data Index: 2688849 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19