Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 82 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8351. Min Range: -4.8351
Max Act: 4.8351. Min Act: -0.1700
Data Index: 7451581 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8351. Min Range: -4.8351
Max Act: 4.8351. Min Act: -0.1700
Data Index: 7135871 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8351. Min Range: -4.8351
Max Act: 4.7726. Min Act: -0.1700
Data Index: 7121941 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8351. Min Range: -4.8351
Max Act: 4.7726. Min Act: -0.1700
Data Index: 6493742 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8351. Min Range: -4.8351
Max Act: 4.7101. Min Act: -0.1700
Data Index: 555371 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8351. Min Range: -4.8351
Max Act: 4.6476. Min Act: -0.1700
Data Index: 5067218 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8351. Min Range: -4.8351
Max Act: 4.6476. Min Act: -0.1700
Data Index: 7489190 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8351. Min Range: -4.8351
Max Act: 4.6164. Min Act: -0.1700
Data Index: 3704103 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8351. Min Range: -4.8351
Max Act: 4.5851. Min Act: -0.1700
Data Index: 1175779 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8351. Min Range: -4.8351
Max Act: 4.5851. Min Act: -0.1700
Data Index: 8345759 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8351. Min Range: -4.8351
Max Act: 4.5539. Min Act: -0.1700
Data Index: 4855589 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8351. Min Range: -4.8351
Max Act: 4.5226. Min Act: -0.1700
Data Index: 2349294 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8351. Min Range: -4.8351
Max Act: 4.5226. Min Act: -0.1700
Data Index: 8449048 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8351. Min Range: -4.8351
Max Act: 4.4914. Min Act: -0.1700
Data Index: 67711 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8351. Min Range: -4.8351
Max Act: 4.5226. Min Act: -0.1700
Data Index: 5921922 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8351. Min Range: -4.8351
Max Act: 4.5226. Min Act: -0.1700
Data Index: 5278666 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8351. Min Range: -4.8351
Max Act: 4.5226. Min Act: -0.1700
Data Index: 3818904 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8351. Min Range: -4.8351
Max Act: 4.5226. Min Act: -0.1700
Data Index: 3747458 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8351. Min Range: -4.8351
Max Act: 4.4914. Min Act: -0.1700
Data Index: 8108709 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8351. Min Range: -4.8351
Max Act: 4.4914. Min Act: -0.1700
Data Index: 6692055 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19