Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3772 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0420. Min Range: -7.0420
Max Act: 7.0420. Min Act: -0.1700
Data Index: 1480369 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0420. Min Range: -7.0420
Max Act: 7.0107. Min Act: -0.1700
Data Index: 7496258 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0420. Min Range: -7.0420
Max Act: 7.0420. Min Act: -0.1700
Data Index: 6249519 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0420. Min Range: -7.0420
Max Act: 6.9170. Min Act: -0.1700
Data Index: 2248162 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0420. Min Range: -7.0420
Max Act: 6.9170. Min Act: -0.1700
Data Index: 341953 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0420. Min Range: -7.0420
Max Act: 6.9170. Min Act: -0.1700
Data Index: 5564616 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0420. Min Range: -7.0420
Max Act: 6.8545. Min Act: -0.1700
Data Index: 7701234 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0420. Min Range: -7.0420
Max Act: 6.8545. Min Act: -0.1700
Data Index: 396722 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0420. Min Range: -7.0420
Max Act: 6.8545. Min Act: -0.1700
Data Index: 7893400 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0420. Min Range: -7.0420
Max Act: 6.8232. Min Act: -0.1700
Data Index: 5380771 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0420. Min Range: -7.0420
Max Act: 6.8232. Min Act: -0.1700
Data Index: 5211453 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0420. Min Range: -7.0420
Max Act: 6.8232. Min Act: -0.1700
Data Index: 1822417 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0420. Min Range: -7.0420
Max Act: 6.7920. Min Act: -0.1700
Data Index: 6769245 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0420. Min Range: -7.0420
Max Act: 6.7920. Min Act: -0.1700
Data Index: 6919825 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0420. Min Range: -7.0420
Max Act: 6.7920. Min Act: -0.1700
Data Index: 3495690 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0420. Min Range: -7.0420
Max Act: 6.7607. Min Act: -0.1700
Data Index: 3981124 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0420. Min Range: -7.0420
Max Act: 6.6982. Min Act: -0.1700
Data Index: 5423466 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0420. Min Range: -7.0420
Max Act: 6.7295. Min Act: -0.1700
Data Index: 5958165 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0420. Min Range: -7.0420
Max Act: 6.7295. Min Act: -0.1700
Data Index: 5799952 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0420. Min Range: -7.0420
Max Act: 6.6982. Min Act: -0.1700
Data Index: 4063148 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19