Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3477 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2910. Min Range: -11.2910
Max Act: 11.2910. Min Act: -0.1700
Data Index: 1378758 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2910. Min Range: -11.2910
Max Act: 11.2285. Min Act: -0.1700
Data Index: 3967821 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2910. Min Range: -11.2910
Max Act: 11.2285. Min Act: -0.1700
Data Index: 7650883 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2910. Min Range: -11.2910
Max Act: 11.1035. Min Act: -0.1700
Data Index: 5380632 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2910. Min Range: -11.2910
Max Act: 11.1035. Min Act: -0.1700
Data Index: 4205653 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2910. Min Range: -11.2910
Max Act: 11.1035. Min Act: -0.1700
Data Index: 8671335 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2910. Min Range: -11.2910
Max Act: 10.9785. Min Act: -0.1700
Data Index: 1672658 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2910. Min Range: -11.2910
Max Act: 10.9785. Min Act: -0.1700
Data Index: 407199 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2910. Min Range: -11.2910
Max Act: 10.9160. Min Act: -0.1700
Data Index: 4768211 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2910. Min Range: -11.2910
Max Act: 10.9160. Min Act: -0.1700
Data Index: 4188569 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2910. Min Range: -11.2910
Max Act: 10.9160. Min Act: -0.1700
Data Index: 1156610 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2910. Min Range: -11.2910
Max Act: 10.9160. Min Act: -0.1700
Data Index: 7721573 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2910. Min Range: -11.2910
Max Act: 10.9160. Min Act: -0.1700
Data Index: 2565254 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2910. Min Range: -11.2910
Max Act: 10.7910. Min Act: -0.1700
Data Index: 5081002 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2910. Min Range: -11.2910
Max Act: 10.8535. Min Act: -0.1700
Data Index: 2666475 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2910. Min Range: -11.2910
Max Act: 10.8535. Min Act: -0.1700
Data Index: 4768204 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2910. Min Range: -11.2910
Max Act: 10.8535. Min Act: -0.1700
Data Index: 4145052 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2910. Min Range: -11.2910
Max Act: 10.8535. Min Act: -0.1700
Data Index: 7531432 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2910. Min Range: -11.2910
Max Act: 10.8535. Min Act: -0.1700
Data Index: 6542319 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2910. Min Range: -11.2910
Max Act: 10.8535. Min Act: -0.1700
Data Index: 4143102 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19