Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3488 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.9479. Min Range: -11.9479
Max Act: 11.9479. Min Act: -0.1700
Data Index: 6660554 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.9479. Min Range: -11.9479
Max Act: 11.6979. Min Act: -0.1700
Data Index: 8008421 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.9479. Min Range: -11.9479
Max Act: 11.6354. Min Act: -0.1700
Data Index: 1918785 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.9479. Min Range: -11.9479
Max Act: 11.5104. Min Act: -0.1700
Data Index: 1221283 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.9479. Min Range: -11.9479
Max Act: 11.4479. Min Act: -0.1700
Data Index: 4059486 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.9479. Min Range: -11.9479
Max Act: 11.3854. Min Act: -0.1700
Data Index: 5845004 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.9479. Min Range: -11.9479
Max Act: 11.3229. Min Act: -0.1700
Data Index: 6767297 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.9479. Min Range: -11.9479
Max Act: 11.3229. Min Act: -0.1700
Data Index: 4215894 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.9479. Min Range: -11.9479
Max Act: 11.1979. Min Act: -0.1700
Data Index: 3280109 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.9479. Min Range: -11.9479
Max Act: 11.1979. Min Act: -0.1700
Data Index: 6691695 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.9479. Min Range: -11.9479
Max Act: 11.1979. Min Act: -0.1700
Data Index: 8348173 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.9479. Min Range: -11.9479
Max Act: 11.1979. Min Act: -0.1700
Data Index: 3658320 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.9479. Min Range: -11.9479
Max Act: 11.1354. Min Act: -0.1700
Data Index: 2804542 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.9479. Min Range: -11.9479
Max Act: 11.0729. Min Act: -0.1700
Data Index: 2105168 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.9479. Min Range: -11.9479
Max Act: 11.0104. Min Act: -0.1700
Data Index: 7545100 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.9479. Min Range: -11.9479
Max Act: 10.9479. Min Act: -0.1700
Data Index: 1844717 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.9479. Min Range: -11.9479
Max Act: 10.9479. Min Act: -0.1700
Data Index: 3413153 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.9479. Min Range: -11.9479
Max Act: 10.8854. Min Act: -0.1700
Data Index: 8242694 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.9479. Min Range: -11.9479
Max Act: 10.9479. Min Act: -0.1700
Data Index: 3585500 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.9479. Min Range: -11.9479
Max Act: 10.8854. Min Act: -0.1700
Data Index: 145010 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19