Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4786 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8495. Min Range: -8.8495
Max Act: 8.8495. Min Act: -0.1700
Data Index: 8666830 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8495. Min Range: -8.8495
Max Act: 8.7245. Min Act: -0.1700
Data Index: 1913339 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8495. Min Range: -8.8495
Max Act: 8.6620. Min Act: -0.1700
Data Index: 4239852 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8495. Min Range: -8.8495
Max Act: 8.5370. Min Act: -0.1700
Data Index: 5491064 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8495. Min Range: -8.8495
Max Act: 8.5370. Min Act: -0.1700
Data Index: 2974350 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8495. Min Range: -8.8495
Max Act: 8.4120. Min Act: -0.1700
Data Index: 3299339 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8495. Min Range: -8.8495
Max Act: 8.3495. Min Act: -0.1700
Data Index: 7034826 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8495. Min Range: -8.8495
Max Act: 8.2558. Min Act: -0.1700
Data Index: 5490866 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8495. Min Range: -8.8495
Max Act: 8.2870. Min Act: -0.1700
Data Index: 5999794 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8495. Min Range: -8.8495
Max Act: 8.2870. Min Act: -0.1700
Data Index: 6617372 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8495. Min Range: -8.8495
Max Act: 8.2558. Min Act: -0.1700
Data Index: 6202303 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8495. Min Range: -8.8495
Max Act: 8.2558. Min Act: -0.1700
Data Index: 5523506 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8495. Min Range: -8.8495
Max Act: 8.2558. Min Act: -0.1700
Data Index: 6456998 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8495. Min Range: -8.8495
Max Act: 8.1620. Min Act: -0.1700
Data Index: 3192240 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8495. Min Range: -8.8495
Max Act: 8.0995. Min Act: -0.1700
Data Index: 2162984 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8495. Min Range: -8.8495
Max Act: 8.0995. Min Act: -0.1700
Data Index: 6778104 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8495. Min Range: -8.8495
Max Act: 8.1308. Min Act: -0.1700
Data Index: 232330 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8495. Min Range: -8.8495
Max Act: 8.1308. Min Act: -0.1700
Data Index: 2674937 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8495. Min Range: -8.8495
Max Act: 8.1308. Min Act: -0.1700
Data Index: 7553993 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8495. Min Range: -8.8495
Max Act: 8.0995. Min Act: -0.1700
Data Index: 4109211 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19