Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3785 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5199. Min Range: -3.5199
Max Act: 3.5199. Min Act: -0.1700
Data Index: 6856110 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5199. Min Range: -3.5199
Max Act: 3.4259. Min Act: -0.1700
Data Index: 1561300 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5199. Min Range: -3.5199
Max Act: 3.4259. Min Act: -0.1700
Data Index: 640259 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5199. Min Range: -3.5199
Max Act: 3.4102. Min Act: -0.1700
Data Index: 885788 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5199. Min Range: -3.5199
Max Act: 3.3632. Min Act: -0.1700
Data Index: 4140073 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5199. Min Range: -3.5199
Max Act: 3.3475. Min Act: -0.1700
Data Index: 3647962 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5199. Min Range: -3.5199
Max Act: 3.3318. Min Act: -0.1700
Data Index: 3177229 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5199. Min Range: -3.5199
Max Act: 3.3004. Min Act: -0.1700
Data Index: 8102041 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5199. Min Range: -3.5199
Max Act: 3.3161. Min Act: -0.1700
Data Index: 394786 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5199. Min Range: -3.5199
Max Act: 3.3004. Min Act: -0.1700
Data Index: 378686 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5199. Min Range: -3.5199
Max Act: 3.3004. Min Act: -0.1700
Data Index: 6987163 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5199. Min Range: -3.5199
Max Act: 3.2690. Min Act: -0.1700
Data Index: 6216835 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5199. Min Range: -3.5199
Max Act: 3.2690. Min Act: -0.1700
Data Index: 2839561 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5199. Min Range: -3.5199
Max Act: 3.2690. Min Act: -0.1700
Data Index: 6716940 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5199. Min Range: -3.5199
Max Act: 3.2690. Min Act: -0.1700
Data Index: 7527130 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5199. Min Range: -3.5199
Max Act: 3.2690. Min Act: -0.1700
Data Index: 3137436 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5199. Min Range: -3.5199
Max Act: 3.2533. Min Act: -0.1700
Data Index: 4902158 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5199. Min Range: -3.5199
Max Act: 3.2376. Min Act: -0.1700
Data Index: 3043963 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5199. Min Range: -3.5199
Max Act: 3.2376. Min Act: -0.1700
Data Index: 1063417 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5199. Min Range: -3.5199
Max Act: 3.2376. Min Act: -0.1700
Data Index: 4862975 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19