Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3717 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0218. Min Range: -8.0218
Max Act: 8.0218. Min Act: -0.1700
Data Index: 1696116 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0218. Min Range: -8.0218
Max Act: 7.8655. Min Act: -0.1700
Data Index: 8526405 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0218. Min Range: -8.0218
Max Act: 7.6780. Min Act: -0.1700
Data Index: 8330272 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0218. Min Range: -8.0218
Max Act: 7.5843. Min Act: -0.1700
Data Index: 5019609 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0218. Min Range: -8.0218
Max Act: 7.4905. Min Act: -0.1700
Data Index: 7691061 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0218. Min Range: -8.0218
Max Act: 7.4905. Min Act: -0.1700
Data Index: 8416764 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0218. Min Range: -8.0218
Max Act: 7.4593. Min Act: -0.1700
Data Index: 4793875 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0218. Min Range: -8.0218
Max Act: 7.3655. Min Act: -0.1700
Data Index: 1355534 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0218. Min Range: -8.0218
Max Act: 7.2718. Min Act: -0.1700
Data Index: 1457826 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0218. Min Range: -8.0218
Max Act: 7.3030. Min Act: -0.1700
Data Index: 6826239 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0218. Min Range: -8.0218
Max Act: 7.2093. Min Act: -0.1700
Data Index: 7038266 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0218. Min Range: -8.0218
Max Act: 7.1780. Min Act: -0.1700
Data Index: 1015106 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0218. Min Range: -8.0218
Max Act: 7.1155. Min Act: -0.1700
Data Index: 7038890 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0218. Min Range: -8.0218
Max Act: 7.1780. Min Act: -0.1700
Data Index: 1758841 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0218. Min Range: -8.0218
Max Act: 7.0530. Min Act: -0.1700
Data Index: 7968897 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0218. Min Range: -8.0218
Max Act: 7.0218. Min Act: -0.1700
Data Index: 4184016 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0218. Min Range: -8.0218
Max Act: 7.0218. Min Act: -0.1700
Data Index: 4142045 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0218. Min Range: -8.0218
Max Act: 6.9905. Min Act: -0.1700
Data Index: 8223732 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0218. Min Range: -8.0218
Max Act: 7.0530. Min Act: -0.1700
Data Index: 4528804 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0218. Min Range: -8.0218
Max Act: 7.0218. Min Act: -0.1700
Data Index: 2757590 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19