Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3681 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8377. Min Range: -3.8377
Max Act: 3.8377. Min Act: -0.1700
Data Index: 4162945 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8377. Min Range: -3.8377
Max Act: 3.7283. Min Act: -0.1700
Data Index: 1887762 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8377. Min Range: -3.8377
Max Act: 3.7126. Min Act: -0.1700
Data Index: 7798218 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8377. Min Range: -3.8377
Max Act: 3.7283. Min Act: -0.1700
Data Index: 2893997 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8377. Min Range: -3.8377
Max Act: 3.6813. Min Act: -0.1700
Data Index: 5642737 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8377. Min Range: -3.8377
Max Act: 3.6344. Min Act: -0.1700
Data Index: 8153042 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8377. Min Range: -3.8377
Max Act: 3.6187. Min Act: -0.1700
Data Index: 6763942 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8377. Min Range: -3.8377
Max Act: 3.5718. Min Act: -0.1700
Data Index: 6823513 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8377. Min Range: -3.8377
Max Act: 3.5561. Min Act: -0.1700
Data Index: 2148945 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8377. Min Range: -3.8377
Max Act: 3.5405. Min Act: -0.1700
Data Index: 3202983 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8377. Min Range: -3.8377
Max Act: 3.5405. Min Act: -0.1700
Data Index: 3782131 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8377. Min Range: -3.8377
Max Act: 3.5092. Min Act: -0.1700
Data Index: 4726584 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8377. Min Range: -3.8377
Max Act: 3.5248. Min Act: -0.1700
Data Index: 5410931 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8377. Min Range: -3.8377
Max Act: 3.5248. Min Act: -0.1700
Data Index: 5064327 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8377. Min Range: -3.8377
Max Act: 3.5248. Min Act: -0.1700
Data Index: 4686378 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8377. Min Range: -3.8377
Max Act: 3.5092. Min Act: -0.1700
Data Index: 7493570 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8377. Min Range: -3.8377
Max Act: 3.4778. Min Act: -0.1700
Data Index: 6903584 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8377. Min Range: -3.8377
Max Act: 3.4622. Min Act: -0.1700
Data Index: 344991 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8377. Min Range: -3.8377
Max Act: 3.4465. Min Act: -0.1700
Data Index: 7322486 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8377. Min Range: -3.8377
Max Act: 3.4308. Min Act: -0.1700
Data Index: 2569063 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19