Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1832 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.2363. Min Act: -0.1700
Data Index: 1100272 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.2051. Min Act: -0.1700
Data Index: 1419039 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.1113. Min Act: -0.1700
Data Index: 2149822 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.0801. Min Act: -0.1700
Data Index: 6057132 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.0488. Min Act: -0.1700
Data Index: 4362537 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2363. Min Range: -4.2363
Max Act: 4.0176. Min Act: -0.1700
Data Index: 2800625 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2363. Min Range: -4.2363
Max Act: 3.9863. Min Act: -0.1700
Data Index: 88208 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2363. Min Range: -4.2363
Max Act: 3.9550. Min Act: -0.1700
Data Index: 6901091 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2363. Min Range: -4.2363
Max Act: 3.9863. Min Act: -0.1700
Data Index: 3857600 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2363. Min Range: -4.2363
Max Act: 3.9550. Min Act: -0.1700
Data Index: 1038786 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2363. Min Range: -4.2363
Max Act: 3.9550. Min Act: -0.1700
Data Index: 2056463 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2363. Min Range: -4.2363
Max Act: 3.8925. Min Act: -0.1700
Data Index: 5050452 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2363. Min Range: -4.2363
Max Act: 3.9238. Min Act: -0.1700
Data Index: 8246540 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2363. Min Range: -4.2363
Max Act: 3.9238. Min Act: -0.1700
Data Index: 7890442 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2363. Min Range: -4.2363
Max Act: 3.9238. Min Act: -0.1700
Data Index: 270827 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2363. Min Range: -4.2363
Max Act: 3.9238. Min Act: -0.1700
Data Index: 2838417 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2363. Min Range: -4.2363
Max Act: 3.8925. Min Act: -0.1700
Data Index: 7387517 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2363. Min Range: -4.2363
Max Act: 3.8925. Min Act: -0.1700
Data Index: 3344854 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2363. Min Range: -4.2363
Max Act: 3.8612. Min Act: -0.1700
Data Index: 706184 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2363. Min Range: -4.2363
Max Act: 3.8612. Min Act: -0.1700
Data Index: 4577936 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19