Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1465 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2667. Min Range: -8.2667
Max Act: 8.2667. Min Act: -0.1700
Data Index: 7019451 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2667. Min Range: -8.2667
Max Act: 8.2042. Min Act: -0.1700
Data Index: 2848775 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2667. Min Range: -8.2667
Max Act: 8.0792. Min Act: -0.1700
Data Index: 4162753 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2667. Min Range: -8.2667
Max Act: 8.0792. Min Act: -0.1700
Data Index: 5146576 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2667. Min Range: -8.2667
Max Act: 7.9542. Min Act: -0.1700
Data Index: 7873969 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2667. Min Range: -8.2667
Max Act: 7.9542. Min Act: -0.1700
Data Index: 7378127 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2667. Min Range: -8.2667
Max Act: 7.8292. Min Act: -0.1700
Data Index: 4388430 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2667. Min Range: -8.2667
Max Act: 7.8917. Min Act: -0.1700
Data Index: 6941193 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2667. Min Range: -8.2667
Max Act: 7.8292. Min Act: -0.1700
Data Index: 3850645 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2667. Min Range: -8.2667
Max Act: 7.8292. Min Act: -0.1699
Data Index: 4022207 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2667. Min Range: -8.2667
Max Act: 7.8292. Min Act: -0.1700
Data Index: 7501735 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2667. Min Range: -8.2667
Max Act: 7.8292. Min Act: -0.1700
Data Index: 5302715 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2667. Min Range: -8.2667
Max Act: 7.8292. Min Act: -0.1700
Data Index: 1159040 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2667. Min Range: -8.2667
Max Act: 7.8292. Min Act: -0.1700
Data Index: 7632399 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2667. Min Range: -8.2667
Max Act: 7.7667. Min Act: -0.1700
Data Index: 1273246 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2667. Min Range: -8.2667
Max Act: 7.7667. Min Act: -0.1700
Data Index: 1843190 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2667. Min Range: -8.2667
Max Act: 7.7667. Min Act: -0.1700
Data Index: 97973 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2667. Min Range: -8.2667
Max Act: 7.7667. Min Act: -0.1700
Data Index: 2285156 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2667. Min Range: -8.2667
Max Act: 7.7667. Min Act: -0.1700
Data Index: 5295398 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2667. Min Range: -8.2667
Max Act: 7.7667. Min Act: -0.1700
Data Index: 2825393 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19