Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1337 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4473. Min Range: -5.4473
Max Act: 5.4473. Min Act: -0.1700
Data Index: 3104486 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4473. Min Range: -5.4473
Max Act: 5.4160. Min Act: -0.1700
Data Index: 7184210 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4473. Min Range: -5.4473
Max Act: 5.4160. Min Act: -0.1700
Data Index: 1528362 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4473. Min Range: -5.4473
Max Act: 5.4160. Min Act: -0.1700
Data Index: 5459559 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4473. Min Range: -5.4473
Max Act: 5.3535. Min Act: -0.1700
Data Index: 6430051 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4473. Min Range: -5.4473
Max Act: 5.2910. Min Act: -0.1700
Data Index: 8115804 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4473. Min Range: -5.4473
Max Act: 5.3535. Min Act: -0.1700
Data Index: 6351491 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4473. Min Range: -5.4473
Max Act: 5.2910. Min Act: -0.1700
Data Index: 3172171 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4473. Min Range: -5.4473
Max Act: 5.2910. Min Act: -0.1700
Data Index: 2237345 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4473. Min Range: -5.4473
Max Act: 5.2285. Min Act: -0.1700
Data Index: 1408844 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4473. Min Range: -5.4473
Max Act: 5.2910. Min Act: -0.1700
Data Index: 5534595 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4473. Min Range: -5.4473
Max Act: 5.2598. Min Act: -0.1700
Data Index: 3556266 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4473. Min Range: -5.4473
Max Act: 5.2285. Min Act: -0.1700
Data Index: 8777717 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4473. Min Range: -5.4473
Max Act: 5.2285. Min Act: -0.1700
Data Index: 8619737 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4473. Min Range: -5.4473
Max Act: 5.1660. Min Act: -0.1700
Data Index: 1304626 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4473. Min Range: -5.4473
Max Act: 5.1660. Min Act: -0.1700
Data Index: 4128927 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4473. Min Range: -5.4473
Max Act: 5.1660. Min Act: -0.1700
Data Index: 5797750 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4473. Min Range: -5.4473
Max Act: 5.1660. Min Act: -0.1700
Data Index: 4765430 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4473. Min Range: -5.4473
Max Act: 5.1348. Min Act: -0.1700
Data Index: 4910776 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4473. Min Range: -5.4473
Max Act: 5.1348. Min Act: -0.1700
Data Index: 5384846 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19