Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 411 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1353. Min Range: -6.1353
Max Act: 6.1353. Min Act: -0.1700
Data Index: 5749627 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1353. Min Range: -6.1353
Max Act: 6.0103. Min Act: -0.1700
Data Index: 7694842 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1353. Min Range: -6.1353
Max Act: 5.9478. Min Act: -0.1700
Data Index: 1914878 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1353. Min Range: -6.1353
Max Act: 5.8540. Min Act: -0.1700
Data Index: 4287726 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1353. Min Range: -6.1353
Max Act: 5.8228. Min Act: -0.1700
Data Index: 1599771 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1353. Min Range: -6.1353
Max Act: 5.7915. Min Act: -0.1700
Data Index: 2486076 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1353. Min Range: -6.1353
Max Act: 5.7290. Min Act: -0.1700
Data Index: 1094829 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1353. Min Range: -6.1353
Max Act: 5.7290. Min Act: -0.1700
Data Index: 7918774 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1353. Min Range: -6.1353
Max Act: 5.7290. Min Act: -0.1700
Data Index: 3630479 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1353. Min Range: -6.1353
Max Act: 5.7290. Min Act: -0.1700
Data Index: 2653299 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1353. Min Range: -6.1353
Max Act: 5.6978. Min Act: -0.1700
Data Index: 7310599 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1353. Min Range: -6.1353
Max Act: 5.6665. Min Act: -0.1700
Data Index: 6242673 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1353. Min Range: -6.1353
Max Act: 5.6665. Min Act: -0.1700
Data Index: 6146370 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1353. Min Range: -6.1353
Max Act: 5.6665. Min Act: -0.1700
Data Index: 4287725 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1353. Min Range: -6.1353
Max Act: 5.5728. Min Act: -0.1700
Data Index: 2684564 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1353. Min Range: -6.1353
Max Act: 5.5728. Min Act: -0.1700
Data Index: 3055128 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1353. Min Range: -6.1353
Max Act: 5.5728. Min Act: -0.1700
Data Index: 1865468 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1353. Min Range: -6.1353
Max Act: 5.5728. Min Act: -0.1700
Data Index: 3816424 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1353. Min Range: -6.1353
Max Act: 5.5415. Min Act: -0.1700
Data Index: 5958700 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1353. Min Range: -6.1353
Max Act: 5.5415. Min Act: -0.1700
Data Index: 6114588 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19