Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3646 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1876. Min Range: -10.1876
Max Act: 10.1876. Min Act: -0.1700
Data Index: 3499090 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1876. Min Range: -10.1876
Max Act: 10.1876. Min Act: -0.1700
Data Index: 6790668 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1876. Min Range: -10.1876
Max Act: 10.1251. Min Act: -0.1700
Data Index: 3646826 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1876. Min Range: -10.1876
Max Act: 10.0001. Min Act: -0.1700
Data Index: 5314830 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1876. Min Range: -10.1876
Max Act: 9.7501. Min Act: -0.1700
Data Index: 1849753 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1876. Min Range: -10.1876
Max Act: 9.6876. Min Act: -0.1700
Data Index: 4637138 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1876. Min Range: -10.1876
Max Act: 9.6876. Min Act: -0.1700
Data Index: 3145564 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1876. Min Range: -10.1876
Max Act: 9.6251. Min Act: -0.1700
Data Index: 4763668 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1876. Min Range: -10.1876
Max Act: 9.6251. Min Act: -0.1700
Data Index: 1998704 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1876. Min Range: -10.1876
Max Act: 9.5626. Min Act: -0.1700
Data Index: 8438709 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1876. Min Range: -10.1876
Max Act: 9.5001. Min Act: -0.1700
Data Index: 1026873 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1876. Min Range: -10.1876
Max Act: 9.5626. Min Act: -0.1700
Data Index: 5068674 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1876. Min Range: -10.1876
Max Act: 9.5626. Min Act: -0.1700
Data Index: 6496937 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1876. Min Range: -10.1876
Max Act: 9.5001. Min Act: -0.1700
Data Index: 8386032 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1876. Min Range: -10.1876
Max Act: 9.5001. Min Act: -0.1700
Data Index: 899989 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1876. Min Range: -10.1876
Max Act: 9.5001. Min Act: -0.1700
Data Index: 1956688 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1876. Min Range: -10.1876
Max Act: 9.5001. Min Act: -0.1700
Data Index: 8630488 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1876. Min Range: -10.1876
Max Act: 9.5001. Min Act: -0.1697
Data Index: 4653726 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1876. Min Range: -10.1876
Max Act: 9.5001. Min Act: -0.1700
Data Index: 4093974 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1876. Min Range: -10.1876
Max Act: 9.5001. Min Act: -0.1700
Data Index: 5952328 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19