Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3445 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.3527. Min Range: -8.3527
Max Act: 8.3527. Min Act: -0.1700
Data Index: 2614205 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3527. Min Range: -8.3527
Max Act: 8.2902. Min Act: -0.1700
Data Index: 1401247 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3527. Min Range: -8.3527
Max Act: 8.1652. Min Act: -0.1700
Data Index: 715061 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3527. Min Range: -8.3527
Max Act: 8.1027. Min Act: -0.1700
Data Index: 1079508 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3527. Min Range: -8.3527
Max Act: 8.0402. Min Act: -0.1700
Data Index: 7947684 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3527. Min Range: -8.3527
Max Act: 7.9777. Min Act: -0.1700
Data Index: 726835 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3527. Min Range: -8.3527
Max Act: 7.9777. Min Act: -0.1700
Data Index: 7389474 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3527. Min Range: -8.3527
Max Act: 7.9777. Min Act: -0.1700
Data Index: 2286273 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3527. Min Range: -8.3527
Max Act: 7.9777. Min Act: -0.1700
Data Index: 6271939 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3527. Min Range: -8.3527
Max Act: 7.9777. Min Act: -0.1700
Data Index: 8529544 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3527. Min Range: -8.3527
Max Act: 7.9152. Min Act: -0.1700
Data Index: 7416560 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3527. Min Range: -8.3527
Max Act: 7.9152. Min Act: -0.1700
Data Index: 3124478 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3527. Min Range: -8.3527
Max Act: 7.9152. Min Act: -0.1700
Data Index: 4085063 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3527. Min Range: -8.3527
Max Act: 7.8527. Min Act: -0.1700
Data Index: 8822621 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3527. Min Range: -8.3527
Max Act: 7.8527. Min Act: -0.1700
Data Index: 6448489 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3527. Min Range: -8.3527
Max Act: 7.8527. Min Act: -0.1700
Data Index: 6682474 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3527. Min Range: -8.3527
Max Act: 7.7902. Min Act: -0.1700
Data Index: 7385708 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3527. Min Range: -8.3527
Max Act: 7.7902. Min Act: -0.1700
Data Index: 7004081 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3527. Min Range: -8.3527
Max Act: 7.7590. Min Act: -0.1700
Data Index: 5008714 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3527. Min Range: -8.3527
Max Act: 7.7590. Min Act: -0.1700
Data Index: 4727773 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19