Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3397 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9394. Min Range: -3.9394
Max Act: 3.9394. Min Act: -0.1700
Data Index: 4475199 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9394. Min Range: -3.9394
Max Act: 3.7518. Min Act: -0.1700
Data Index: 8468513 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9394. Min Range: -3.9394
Max Act: 3.6579. Min Act: -0.1700
Data Index: 7463318 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9394. Min Range: -3.9394
Max Act: 3.6266. Min Act: -0.1700
Data Index: 1115963 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9394. Min Range: -3.9394
Max Act: 3.6266. Min Act: -0.1700
Data Index: 5642091 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9394. Min Range: -3.9394
Max Act: 3.6266. Min Act: -0.1700
Data Index: 3349391 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9394. Min Range: -3.9394
Max Act: 3.5953. Min Act: -0.1700
Data Index: 843704 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9394. Min Range: -3.9394
Max Act: 3.5953. Min Act: -0.1700
Data Index: 7359818 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9394. Min Range: -3.9394
Max Act: 3.6266. Min Act: -0.1700
Data Index: 6703807 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9394. Min Range: -3.9394
Max Act: 3.5327. Min Act: -0.1700
Data Index: 2005415 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9394. Min Range: -3.9394
Max Act: 3.5327. Min Act: -0.1700
Data Index: 2957509 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9394. Min Range: -3.9394
Max Act: 3.5014. Min Act: -0.1700
Data Index: 1065069 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9394. Min Range: -3.9394
Max Act: 3.5014. Min Act: -0.1700
Data Index: 4774052 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9394. Min Range: -3.9394
Max Act: 3.4857. Min Act: -0.1700
Data Index: 1551212 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9394. Min Range: -3.9394
Max Act: 3.5014. Min Act: -0.1700
Data Index: 7601128 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9394. Min Range: -3.9394
Max Act: 3.4701. Min Act: -0.1700
Data Index: 4750041 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9394. Min Range: -3.9394
Max Act: 3.4701. Min Act: -0.1700
Data Index: 4175658 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9394. Min Range: -3.9394
Max Act: 3.4701. Min Act: -0.1700
Data Index: 6061441 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9394. Min Range: -3.9394
Max Act: 3.4387. Min Act: -0.1700
Data Index: 5621685 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9394. Min Range: -3.9394
Max Act: 3.4387. Min Act: -0.1700
Data Index: 2038704 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #19