Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2707 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3248. Min Range: -8.3248
Max Act: 8.3248. Min Act: -0.1700
Data Index: 537078 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3248. Min Range: -8.3248
Max Act: 8.3248. Min Act: -0.1700
Data Index: 3685427 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3248. Min Range: -8.3248
Max Act: 8.1373. Min Act: -0.1700
Data Index: 5584033 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3248. Min Range: -8.3248
Max Act: 8.1373. Min Act: -0.1700
Data Index: 831742 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3248. Min Range: -8.3248
Max Act: 8.1373. Min Act: -0.1700
Data Index: 500402 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3248. Min Range: -8.3248
Max Act: 8.0748. Min Act: -0.1700
Data Index: 1136512 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3248. Min Range: -8.3248
Max Act: 8.0748. Min Act: -0.1700
Data Index: 5215548 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3248. Min Range: -8.3248
Max Act: 8.0748. Min Act: -0.1700
Data Index: 8795699 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3248. Min Range: -8.3248
Max Act: 8.0123. Min Act: -0.1700
Data Index: 5595823 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3248. Min Range: -8.3248
Max Act: 8.0123. Min Act: -0.1700
Data Index: 1592097 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3248. Min Range: -8.3248
Max Act: 7.9498. Min Act: -0.1700
Data Index: 4035544 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3248. Min Range: -8.3248
Max Act: 7.8873. Min Act: -0.1700
Data Index: 6268440 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3248. Min Range: -8.3248
Max Act: 7.8248. Min Act: -0.1700
Data Index: 807008 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3248. Min Range: -8.3248
Max Act: 7.8248. Min Act: -0.1700
Data Index: 662010 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3248. Min Range: -8.3248
Max Act: 7.7623. Min Act: -0.1700
Data Index: 476131 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3248. Min Range: -8.3248
Max Act: 7.6686. Min Act: -0.1700
Data Index: 3662847 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3248. Min Range: -8.3248
Max Act: 7.6998. Min Act: -0.1700
Data Index: 5513184 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3248. Min Range: -8.3248
Max Act: 7.6686. Min Act: -0.1700
Data Index: 5627814 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3248. Min Range: -8.3248
Max Act: 7.6373. Min Act: -0.1700
Data Index: 8484994 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3248. Min Range: -8.3248
Max Act: 7.6061. Min Act: -0.1700
Data Index: 7655065 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19