Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3514 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4339. Min Range: -10.4339
Max Act: 10.4339. Min Act: -0.1700
Data Index: 1069379 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4339. Min Range: -10.4339
Max Act: 10.4339. Min Act: -0.1700
Data Index: 951166 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4339. Min Range: -10.4339
Max Act: 10.2464. Min Act: -0.1700
Data Index: 5446637 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4339. Min Range: -10.4339
Max Act: 10.1214. Min Act: -0.1700
Data Index: 6901641 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4339. Min Range: -10.4339
Max Act: 9.9339. Min Act: -0.1700
Data Index: 8385642 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4339. Min Range: -10.4339
Max Act: 9.8714. Min Act: -0.1700
Data Index: 2142872 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4339. Min Range: -10.4339
Max Act: 9.8089. Min Act: -0.1700
Data Index: 1998848 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4339. Min Range: -10.4339
Max Act: 9.8089. Min Act: -0.1700
Data Index: 1419039 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4339. Min Range: -10.4339
Max Act: 9.6839. Min Act: -0.1700
Data Index: 1692731 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4339. Min Range: -10.4339
Max Act: 9.6214. Min Act: -0.1700
Data Index: 5166602 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4339. Min Range: -10.4339
Max Act: 9.5589. Min Act: -0.1700
Data Index: 900684 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4339. Min Range: -10.4339
Max Act: 9.4964. Min Act: -0.1700
Data Index: 6026977 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4339. Min Range: -10.4339
Max Act: 9.4964. Min Act: -0.1700
Data Index: 8424283 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4339. Min Range: -10.4339
Max Act: 9.4339. Min Act: -0.1700
Data Index: 8534626 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4339. Min Range: -10.4339
Max Act: 9.3714. Min Act: -0.1700
Data Index: 3662724 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4339. Min Range: -10.4339
Max Act: 9.3714. Min Act: -0.1700
Data Index: 3409917 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4339. Min Range: -10.4339
Max Act: 9.3714. Min Act: -0.1700
Data Index: 6282728 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4339. Min Range: -10.4339
Max Act: 9.3714. Min Act: -0.1700
Data Index: 5824074 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4339. Min Range: -10.4339
Max Act: 9.3089. Min Act: -0.1700
Data Index: 6221629 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4339. Min Range: -10.4339
Max Act: 9.3089. Min Act: -0.1700
Data Index: 1716227 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19