Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0820. Min Range: -7.0820
Max Act: 7.0820. Min Act: -0.1700
Data Index: 2647262 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0820. Min Range: -7.0820
Max Act: 6.9882. Min Act: -0.1700
Data Index: 5509370 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0820. Min Range: -7.0820
Max Act: 6.7695. Min Act: -0.1700
Data Index: 5752358 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0820. Min Range: -7.0820
Max Act: 6.7070. Min Act: -0.1700
Data Index: 5565866 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0820. Min Range: -7.0820
Max Act: 6.5507. Min Act: -0.1700
Data Index: 5749359 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0820. Min Range: -7.0820
Max Act: 6.5195. Min Act: -0.1700
Data Index: 7714754 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0820. Min Range: -7.0820
Max Act: 6.4257. Min Act: -0.1700
Data Index: 8154383 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0820. Min Range: -7.0820
Max Act: 6.4257. Min Act: -0.1700
Data Index: 8048376 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0820. Min Range: -7.0820
Max Act: 6.3632. Min Act: -0.1700
Data Index: 7994956 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0820. Min Range: -7.0820
Max Act: 6.3632. Min Act: -0.1700
Data Index: 4880578 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0820. Min Range: -7.0820
Max Act: 6.3007. Min Act: -0.1700
Data Index: 1315044 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0820. Min Range: -7.0820
Max Act: 6.3320. Min Act: -0.1700
Data Index: 1849045 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0820. Min Range: -7.0820
Max Act: 6.3320. Min Act: -0.1700
Data Index: 7673776 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0820. Min Range: -7.0820
Max Act: 6.3007. Min Act: -0.1700
Data Index: 7926885 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0820. Min Range: -7.0820
Max Act: 6.2695. Min Act: -0.1700
Data Index: 3373889 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0820. Min Range: -7.0820
Max Act: 6.2695. Min Act: -0.1700
Data Index: 1942106 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0820. Min Range: -7.0820
Max Act: 6.3007. Min Act: -0.1700
Data Index: 2217891 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0820. Min Range: -7.0820
Max Act: 6.2070. Min Act: -0.1700
Data Index: 3922885 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0820. Min Range: -7.0820
Max Act: 6.1757. Min Act: -0.1700
Data Index: 3167323 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0820. Min Range: -7.0820
Max Act: 6.2070. Min Act: -0.1700
Data Index: 4744603 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19