Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 36 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8297. Min Range: -3.8297
Max Act: 3.7984. Min Act: -0.1700
Data Index: 8680932 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8297. Min Range: -3.8297
Max Act: 3.8297. Min Act: -0.1700
Data Index: 2886629 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8297. Min Range: -3.8297
Max Act: 3.7672. Min Act: -0.1700
Data Index: 4437478 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8297. Min Range: -3.8297
Max Act: 3.7359. Min Act: -0.1700
Data Index: 5296141 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8297. Min Range: -3.8297
Max Act: 3.7359. Min Act: -0.1700
Data Index: 2705373 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8297. Min Range: -3.8297
Max Act: 3.7359. Min Act: -0.1700
Data Index: 7898280 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8297. Min Range: -3.8297
Max Act: 3.7046. Min Act: -0.1700
Data Index: 5135972 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8297. Min Range: -3.8297
Max Act: 3.6733. Min Act: -0.1700
Data Index: 5664729 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8297. Min Range: -3.8297
Max Act: 3.6733. Min Act: -0.1700
Data Index: 4291185 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8297. Min Range: -3.8297
Max Act: 3.6420. Min Act: -0.1700
Data Index: 5054991 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8297. Min Range: -3.8297
Max Act: 3.6733. Min Act: -0.1700
Data Index: 6379843 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8297. Min Range: -3.8297
Max Act: 3.6733. Min Act: -0.1700
Data Index: 1209090 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8297. Min Range: -3.8297
Max Act: 3.6733. Min Act: -0.1700
Data Index: 7578359 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8297. Min Range: -3.8297
Max Act: 3.6420. Min Act: -0.1700
Data Index: 847561 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8297. Min Range: -3.8297
Max Act: 3.6420. Min Act: -0.1700
Data Index: 3575696 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8297. Min Range: -3.8297
Max Act: 3.6420. Min Act: -0.1700
Data Index: 7332352 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8297. Min Range: -3.8297
Max Act: 3.6420. Min Act: -0.1700
Data Index: 6996654 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8297. Min Range: -3.8297
Max Act: 3.6420. Min Act: -0.1700
Data Index: 2644374 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8297. Min Range: -3.8297
Max Act: 3.6420. Min Act: -0.1700
Data Index: 4625749 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8297. Min Range: -3.8297
Max Act: 3.6420. Min Act: -0.1700
Data Index: 6343746 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19