Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1127 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4840. Min Range: -6.4840
Max Act: 6.4840. Min Act: -0.1700
Data Index: 2627954 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4840. Min Range: -6.4840
Max Act: 6.4840. Min Act: -0.1700
Data Index: 313396 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4840. Min Range: -6.4840
Max Act: 6.4215. Min Act: -0.1700
Data Index: 1717832 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4840. Min Range: -6.4840
Max Act: 6.3590. Min Act: -0.1700
Data Index: 4412776 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4840. Min Range: -6.4840
Max Act: 6.2965. Min Act: -0.1700
Data Index: 5609634 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4840. Min Range: -6.4840
Max Act: 6.2027. Min Act: -0.1700
Data Index: 4163821 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4840. Min Range: -6.4840
Max Act: 6.2027. Min Act: -0.1700
Data Index: 5991516 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4840. Min Range: -6.4840
Max Act: 6.1715. Min Act: -0.1700
Data Index: 8418296 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4840. Min Range: -6.4840
Max Act: 6.1715. Min Act: -0.1700
Data Index: 7330136 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4840. Min Range: -6.4840
Max Act: 6.1402. Min Act: -0.1700
Data Index: 6730559 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4840. Min Range: -6.4840
Max Act: 6.1090. Min Act: -0.1700
Data Index: 6325741 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4840. Min Range: -6.4840
Max Act: 6.1402. Min Act: -0.1700
Data Index: 4708772 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4840. Min Range: -6.4840
Max Act: 6.1402. Min Act: -0.1700
Data Index: 5972546 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4840. Min Range: -6.4840
Max Act: 6.1090. Min Act: -0.1700
Data Index: 8626326 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4840. Min Range: -6.4840
Max Act: 6.1090. Min Act: -0.1700
Data Index: 6716868 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4840. Min Range: -6.4840
Max Act: 6.0777. Min Act: -0.1700
Data Index: 446494 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4840. Min Range: -6.4840
Max Act: 6.0465. Min Act: -0.1700
Data Index: 7534886 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4840. Min Range: -6.4840
Max Act: 6.0465. Min Act: -0.1700
Data Index: 703010 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4840. Min Range: -6.4840
Max Act: 6.0465. Min Act: -0.1700
Data Index: 6902324 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4840. Min Range: -6.4840
Max Act: 6.0152. Min Act: -0.1700
Data Index: 3652732 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19