Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3360 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3545. Min Range: -6.3545
Max Act: 6.3545. Min Act: -0.1700
Data Index: 3347582 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3545. Min Range: -6.3545
Max Act: 6.0420. Min Act: -0.1700
Data Index: 5520281 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3545. Min Range: -6.3545
Max Act: 5.8545. Min Act: -0.1700
Data Index: 2441423 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3545. Min Range: -6.3545
Max Act: 5.7607. Min Act: -0.1700
Data Index: 3030572 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3545. Min Range: -6.3545
Max Act: 5.7607. Min Act: -0.1700
Data Index: 1785798 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3545. Min Range: -6.3545
Max Act: 5.7607. Min Act: -0.1700
Data Index: 7878982 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3545. Min Range: -6.3545
Max Act: 5.7295. Min Act: -0.1700
Data Index: 8161509 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3545. Min Range: -6.3545
Max Act: 5.7295. Min Act: -0.1700
Data Index: 8656071 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3545. Min Range: -6.3545
Max Act: 5.6982. Min Act: -0.1700
Data Index: 3422812 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3545. Min Range: -6.3545
Max Act: 5.7295. Min Act: -0.1700
Data Index: 5054567 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3545. Min Range: -6.3545
Max Act: 5.7295. Min Act: -0.1700
Data Index: 7233899 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3545. Min Range: -6.3545
Max Act: 5.6982. Min Act: -0.1700
Data Index: 382033 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3545. Min Range: -6.3545
Max Act: 5.7295. Min Act: -0.1700
Data Index: 577957 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3545. Min Range: -6.3545
Max Act: 5.6670. Min Act: -0.1700
Data Index: 7087314 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3545. Min Range: -6.3545
Max Act: 5.6670. Min Act: -0.1700
Data Index: 2717843 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3545. Min Range: -6.3545
Max Act: 5.6045. Min Act: -0.1700
Data Index: 5057045 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3545. Min Range: -6.3545
Max Act: 5.6045. Min Act: -0.1700
Data Index: 4776733 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3545. Min Range: -6.3545
Max Act: 5.5420. Min Act: -0.1700
Data Index: 2441239 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3545. Min Range: -6.3545
Max Act: 5.5420. Min Act: -0.1700
Data Index: 4003215 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3545. Min Range: -6.3545
Max Act: 5.5107. Min Act: -0.1700
Data Index: 6918096 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19