Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2650 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2830. Min Range: -6.2830
Max Act: 6.2830. Min Act: -0.1700
Data Index: 297539 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2830. Min Range: -6.2830
Max Act: 6.0955. Min Act: -0.1700
Data Index: 1899945 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2830. Min Range: -6.2830
Max Act: 6.0955. Min Act: -0.1700
Data Index: 1893859 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2830. Min Range: -6.2830
Max Act: 6.0018. Min Act: -0.1700
Data Index: 5052738 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2830. Min Range: -6.2830
Max Act: 5.9393. Min Act: -0.1700
Data Index: 3945107 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2830. Min Range: -6.2830
Max Act: 5.8768. Min Act: -0.1700
Data Index: 5361451 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2830. Min Range: -6.2830
Max Act: 5.8455. Min Act: -0.1700
Data Index: 954281 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2830. Min Range: -6.2830
Max Act: 5.8143. Min Act: -0.1700
Data Index: 8202307 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2830. Min Range: -6.2830
Max Act: 5.7830. Min Act: -0.1700
Data Index: 361843 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2830. Min Range: -6.2830
Max Act: 5.7830. Min Act: -0.1700
Data Index: 8302573 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2830. Min Range: -6.2830
Max Act: 5.7830. Min Act: -0.1700
Data Index: 7374614 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2830. Min Range: -6.2830
Max Act: 5.7830. Min Act: -0.1700
Data Index: 496483 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2830. Min Range: -6.2830
Max Act: 5.7518. Min Act: -0.1700
Data Index: 2270442 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2830. Min Range: -6.2830
Max Act: 5.7518. Min Act: -0.1700
Data Index: 4083320 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2830. Min Range: -6.2830
Max Act: 5.7518. Min Act: -0.1700
Data Index: 6679807 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2830. Min Range: -6.2830
Max Act: 5.7205. Min Act: -0.1700
Data Index: 6014991 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2830. Min Range: -6.2830
Max Act: 5.7205. Min Act: -0.1700
Data Index: 6452982 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2830. Min Range: -6.2830
Max Act: 5.7205. Min Act: -0.1700
Data Index: 605370 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2830. Min Range: -6.2830
Max Act: 5.7205. Min Act: -0.1700
Data Index: 4444826 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2830. Min Range: -6.2830
Max Act: 5.6893. Min Act: -0.1700
Data Index: 6844057 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19