Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4160 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7629. Min Range: -10.7629
Max Act: 10.7004. Min Act: -0.1700
Data Index: 894894 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7629. Min Range: -10.7629
Max Act: 10.7629. Min Act: -0.1700
Data Index: 690827 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7629. Min Range: -10.7629
Max Act: 10.7629. Min Act: -0.1700
Data Index: 2793182 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7629. Min Range: -10.7629
Max Act: 10.7004. Min Act: -0.1700
Data Index: 8055400 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7629. Min Range: -10.7629
Max Act: 10.7004. Min Act: -0.1700
Data Index: 123073 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7629. Min Range: -10.7629
Max Act: 10.7004. Min Act: -0.1700
Data Index: 3177031 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7629. Min Range: -10.7629
Max Act: 10.7004. Min Act: -0.1699
Data Index: 1565861 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7629. Min Range: -10.7629
Max Act: 10.6379. Min Act: -0.1700
Data Index: 8459317 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7629. Min Range: -10.7629
Max Act: 10.6379. Min Act: -0.1700
Data Index: 662233 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7629. Min Range: -10.7629
Max Act: 10.5754. Min Act: -0.1700
Data Index: 2056120 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7629. Min Range: -10.7629
Max Act: 10.5129. Min Act: -0.1700
Data Index: 6155857 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7629. Min Range: -10.7629
Max Act: 10.5754. Min Act: -0.1697
Data Index: 3083519 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7629. Min Range: -10.7629
Max Act: 10.5754. Min Act: -0.1696
Data Index: 5173290 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7629. Min Range: -10.7629
Max Act: 10.5754. Min Act: -0.1696
Data Index: 7219405 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7629. Min Range: -10.7629
Max Act: 10.5754. Min Act: -0.1700
Data Index: 3531364 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7629. Min Range: -10.7629
Max Act: 10.5754. Min Act: -0.1700
Data Index: 6742713 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7629. Min Range: -10.7629
Max Act: 10.5129. Min Act: -0.1700
Data Index: 3938456 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7629. Min Range: -10.7629
Max Act: 10.5129. Min Act: -0.1694
Data Index: 5284750 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7629. Min Range: -10.7629
Max Act: 10.5129. Min Act: -0.1700
Data Index: 6110282 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7629. Min Range: -10.7629
Max Act: 10.4504. Min Act: -0.1700
Data Index: 4514223 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19