Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4074 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8608. Min Range: -6.8608
Max Act: 6.8608. Min Act: -0.1700
Data Index: 711289 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8608. Min Range: -6.8608
Max Act: 6.7358. Min Act: -0.1700
Data Index: 7169453 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8608. Min Range: -6.8608
Max Act: 6.5171. Min Act: -0.1700
Data Index: 6807936 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8608. Min Range: -6.8608
Max Act: 6.5171. Min Act: -0.1700
Data Index: 1465538 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8608. Min Range: -6.8608
Max Act: 6.4858. Min Act: -0.1700
Data Index: 4566323 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8608. Min Range: -6.8608
Max Act: 6.4546. Min Act: -0.1700
Data Index: 4704245 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8608. Min Range: -6.8608
Max Act: 6.4233. Min Act: -0.1700
Data Index: 6984833 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8608. Min Range: -6.8608
Max Act: 6.4546. Min Act: -0.1700
Data Index: 4465643 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8608. Min Range: -6.8608
Max Act: 6.3921. Min Act: -0.1700
Data Index: 5081343 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8608. Min Range: -6.8608
Max Act: 6.3608. Min Act: -0.1700
Data Index: 7309721 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8608. Min Range: -6.8608
Max Act: 6.3921. Min Act: -0.1700
Data Index: 6266923 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8608. Min Range: -6.8608
Max Act: 6.3608. Min Act: -0.1700
Data Index: 3661200 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8608. Min Range: -6.8608
Max Act: 6.3608. Min Act: -0.1700
Data Index: 5536904 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8608. Min Range: -6.8608
Max Act: 6.3296. Min Act: -0.1700
Data Index: 656862 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8608. Min Range: -6.8608
Max Act: 6.3296. Min Act: -0.1700
Data Index: 2939076 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8608. Min Range: -6.8608
Max Act: 6.2983. Min Act: -0.1700
Data Index: 5828659 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8608. Min Range: -6.8608
Max Act: 6.2358. Min Act: -0.1700
Data Index: 1174702 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8608. Min Range: -6.8608
Max Act: 6.2983. Min Act: -0.1700
Data Index: 2910372 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8608. Min Range: -6.8608
Max Act: 6.2983. Min Act: -0.1700
Data Index: 6616714 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8608. Min Range: -6.8608
Max Act: 6.2983. Min Act: -0.1700
Data Index: 775064 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19