Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 999 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8729. Min Range: -5.8729
Max Act: 5.8729. Min Act: -0.1700
Data Index: 1852866 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8729. Min Range: -5.8729
Max Act: 5.8416. Min Act: -0.1700
Data Index: 1315534 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8729. Min Range: -5.8729
Max Act: 5.7791. Min Act: -0.1700
Data Index: 665629 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8729. Min Range: -5.8729
Max Act: 5.7791. Min Act: -0.1700
Data Index: 7816655 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8729. Min Range: -5.8729
Max Act: 5.8104. Min Act: -0.1700
Data Index: 8401568 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8729. Min Range: -5.8729
Max Act: 5.8104. Min Act: -0.1700
Data Index: 7127274 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8729. Min Range: -5.8729
Max Act: 5.7479. Min Act: -0.1700
Data Index: 3748205 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8729. Min Range: -5.8729
Max Act: 5.7479. Min Act: -0.1700
Data Index: 4814613 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8729. Min Range: -5.8729
Max Act: 5.7479. Min Act: -0.1700
Data Index: 3590168 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8729. Min Range: -5.8729
Max Act: 5.7166. Min Act: -0.1700
Data Index: 2288677 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8729. Min Range: -5.8729
Max Act: 5.7166. Min Act: -0.1700
Data Index: 8825564 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8729. Min Range: -5.8729
Max Act: 5.7166. Min Act: -0.1700
Data Index: 2751790 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8729. Min Range: -5.8729
Max Act: 5.6854. Min Act: -0.1700
Data Index: 300840 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8729. Min Range: -5.8729
Max Act: 5.6854. Min Act: -0.1700
Data Index: 8575004 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8729. Min Range: -5.8729
Max Act: 5.7166. Min Act: -0.1700
Data Index: 5852919 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8729. Min Range: -5.8729
Max Act: 5.6854. Min Act: -0.1700
Data Index: 4095190 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8729. Min Range: -5.8729
Max Act: 5.6541. Min Act: -0.1700
Data Index: 1494831 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8729. Min Range: -5.8729
Max Act: 5.6541. Min Act: -0.1700
Data Index: 8640385 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8729. Min Range: -5.8729
Max Act: 5.6229. Min Act: -0.1700
Data Index: 8623551 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8729. Min Range: -5.8729
Max Act: 5.6541. Min Act: -0.1700
Data Index: 4065008 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19