Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1673 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.5053. Min Act: -0.1700
Data Index: 1838662 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.4115. Min Act: -0.1700
Data Index: 8139379 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.3803. Min Act: -0.1700
Data Index: 7356693 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.3490. Min Act: -0.1700
Data Index: 8690255 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.3490. Min Act: -0.1700
Data Index: 8524309 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.3490. Min Act: -0.1700
Data Index: 4044518 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.3490. Min Act: -0.1700
Data Index: 7812608 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.3178. Min Act: -0.1700
Data Index: 6907743 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.3178. Min Act: -0.1700
Data Index: 8408144 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.3178. Min Act: -0.1700
Data Index: 5996695 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.3178. Min Act: -0.1699
Data Index: 4350101 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.3178. Min Act: -0.1700
Data Index: 828709 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.3178. Min Act: -0.1700
Data Index: 2898995 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.2865. Min Act: -0.1700
Data Index: 5048600 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.2865. Min Act: -0.1700
Data Index: 1629792 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.2553. Min Act: -0.1700
Data Index: 6658116 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.2553. Min Act: -0.1700
Data Index: 5586293 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.2553. Min Act: -0.1700
Data Index: 7502161 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.2553. Min Act: -0.1700
Data Index: 8203515 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5053. Min Range: -5.5053
Max Act: 5.2553. Min Act: -0.1700
Data Index: 8203520 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19