Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3902 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9587. Min Range: -3.9587
Max Act: 3.9587. Min Act: -0.1700
Data Index: 5255428 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9587. Min Range: -3.9587
Max Act: 3.9587. Min Act: -0.1700
Data Index: 2606585 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9587. Min Range: -3.9587
Max Act: 3.9274. Min Act: -0.1700
Data Index: 8219077 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9587. Min Range: -3.9587
Max Act: 3.9274. Min Act: -0.1700
Data Index: 8240743 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9587. Min Range: -3.9587
Max Act: 3.8962. Min Act: -0.1700
Data Index: 6547041 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9587. Min Range: -3.9587
Max Act: 3.8962. Min Act: -0.1700
Data Index: 5710447 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9587. Min Range: -3.9587
Max Act: 3.8649. Min Act: -0.1700
Data Index: 5669774 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9587. Min Range: -3.9587
Max Act: 3.8649. Min Act: -0.1700
Data Index: 4808280 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9587. Min Range: -3.9587
Max Act: 3.8336. Min Act: -0.1700
Data Index: 4716266 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9587. Min Range: -3.9587
Max Act: 3.8649. Min Act: -0.1700
Data Index: 7010362 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9587. Min Range: -3.9587
Max Act: 3.8493. Min Act: -0.1700
Data Index: 4993712 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9587. Min Range: -3.9587
Max Act: 3.8336. Min Act: -0.1700
Data Index: 8363762 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9587. Min Range: -3.9587
Max Act: 3.8493. Min Act: -0.1700
Data Index: 6783939 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9587. Min Range: -3.9587
Max Act: 3.8180. Min Act: -0.1700
Data Index: 2084449 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9587. Min Range: -3.9587
Max Act: 3.8336. Min Act: -0.1700
Data Index: 2817521 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9587. Min Range: -3.9587
Max Act: 3.8180. Min Act: -0.1700
Data Index: 7823471 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9587. Min Range: -3.9587
Max Act: 3.8023. Min Act: -0.1700
Data Index: 5129226 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9587. Min Range: -3.9587
Max Act: 3.7867. Min Act: -0.1700
Data Index: 7803929 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9587. Min Range: -3.9587
Max Act: 3.7867. Min Act: -0.1700
Data Index: 6193328 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9587. Min Range: -3.9587
Max Act: 3.7711. Min Act: -0.1700
Data Index: 2682642 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #19