Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3610 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1380. Min Range: -3.1380
Max Act: 3.1380. Min Act: -0.1700
Data Index: 58633 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1380. Min Range: -3.1380
Max Act: 3.0908. Min Act: -0.1700
Data Index: 6016270 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1380. Min Range: -3.1380
Max Act: 3.1065. Min Act: -0.1700
Data Index: 8729851 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1380. Min Range: -3.1380
Max Act: 3.1065. Min Act: -0.1700
Data Index: 563503 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1380. Min Range: -3.1380
Max Act: 3.0908. Min Act: -0.1700
Data Index: 3764627 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1380. Min Range: -3.1380
Max Act: 3.0908. Min Act: -0.1700
Data Index: 3091548 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1380. Min Range: -3.1380
Max Act: 3.0908. Min Act: -0.1700
Data Index: 765577 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1380. Min Range: -3.1380
Max Act: 3.0908. Min Act: -0.1700
Data Index: 58634 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1380. Min Range: -3.1380
Max Act: 3.0908. Min Act: -0.1700
Data Index: 8814465 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1380. Min Range: -3.1380
Max Act: 3.0750. Min Act: -0.1700
Data Index: 1030429 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1380. Min Range: -3.1380
Max Act: 3.0750. Min Act: -0.1700
Data Index: 6889013 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1380. Min Range: -3.1380
Max Act: 3.0750. Min Act: -0.1700
Data Index: 1477590 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1380. Min Range: -3.1380
Max Act: 3.0750. Min Act: -0.1700
Data Index: 1050041 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1380. Min Range: -3.1380
Max Act: 3.0750. Min Act: -0.1700
Data Index: 4456078 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1380. Min Range: -3.1380
Max Act: 3.0750. Min Act: -0.1700
Data Index: 8555886 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1380. Min Range: -3.1380
Max Act: 3.0750. Min Act: -0.1700
Data Index: 2504169 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1380. Min Range: -3.1380
Max Act: 3.0750. Min Act: -0.1700
Data Index: 4284698 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1380. Min Range: -3.1380
Max Act: 3.0750. Min Act: -0.1700
Data Index: 2500098 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1380. Min Range: -3.1380
Max Act: 3.0592. Min Act: -0.1700
Data Index: 7070665 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1380. Min Range: -3.1380
Max Act: 3.0592. Min Act: -0.1700
Data Index: 3330526 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19