Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3252 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4314. Min Range: -8.4314
Max Act: 8.4314. Min Act: -0.1700
Data Index: 1889141 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4314. Min Range: -8.4314
Max Act: 8.1814. Min Act: -0.1700
Data Index: 1889142 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4314. Min Range: -8.4314
Max Act: 8.1189. Min Act: -0.1700
Data Index: 1231658 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4314. Min Range: -8.4314
Max Act: 7.9001. Min Act: -0.1700
Data Index: 1254633 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4314. Min Range: -8.4314
Max Act: 7.9314. Min Act: -0.1700
Data Index: 3891444 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4314. Min Range: -8.4314
Max Act: 7.8689. Min Act: -0.1700
Data Index: 6194370 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4314. Min Range: -8.4314
Max Act: 7.7751. Min Act: -0.1700
Data Index: 5048954 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4314. Min Range: -8.4314
Max Act: 7.7439. Min Act: -0.1700
Data Index: 5123463 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4314. Min Range: -8.4314
Max Act: 7.7439. Min Act: -0.1700
Data Index: 5509699 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4314. Min Range: -8.4314
Max Act: 7.6501. Min Act: -0.1700
Data Index: 3947930 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4314. Min Range: -8.4314
Max Act: 7.5876. Min Act: -0.1700
Data Index: 5210828 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4314. Min Range: -8.4314
Max Act: 7.5876. Min Act: -0.1700
Data Index: 2210929 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4314. Min Range: -8.4314
Max Act: 7.5564. Min Act: -0.1700
Data Index: 130421 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4314. Min Range: -8.4314
Max Act: 7.5564. Min Act: -0.1700
Data Index: 8220034 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4314. Min Range: -8.4314
Max Act: 7.4001. Min Act: -0.1700
Data Index: 4920156 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4314. Min Range: -8.4314
Max Act: 7.4314. Min Act: -0.1700
Data Index: 3989490 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4314. Min Range: -8.4314
Max Act: 7.3689. Min Act: -0.1700
Data Index: 8574709 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4314. Min Range: -8.4314
Max Act: 7.3689. Min Act: -0.1700
Data Index: 1231657 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4314. Min Range: -8.4314
Max Act: 7.3689. Min Act: -0.1700
Data Index: 4857274 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4314. Min Range: -8.4314
Max Act: 7.3689. Min Act: -0.1700
Data Index: 7913748 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19