Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5688 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0322. Min Range: -4.0322
Max Act: 4.0009. Min Act: -0.1700
Data Index: 4203280 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0322. Min Range: -4.0322
Max Act: 4.0322. Min Act: -0.1700
Data Index: 6285352 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0322. Min Range: -4.0322
Max Act: 3.9697. Min Act: -0.1700
Data Index: 4430841 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0322. Min Range: -4.0322
Max Act: 3.9071. Min Act: -0.1700
Data Index: 997243 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0322. Min Range: -4.0322
Max Act: 3.8915. Min Act: -0.1700
Data Index: 3776442 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0322. Min Range: -4.0322
Max Act: 3.8602. Min Act: -0.1700
Data Index: 8751330 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0322. Min Range: -4.0322
Max Act: 3.8133. Min Act: -0.1700
Data Index: 1310691 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0322. Min Range: -4.0322
Max Act: 3.8133. Min Act: -0.1700
Data Index: 2246788 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0322. Min Range: -4.0322
Max Act: 3.8133. Min Act: -0.1700
Data Index: 5924823 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0322. Min Range: -4.0322
Max Act: 3.7977. Min Act: -0.1700
Data Index: 2506499 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0322. Min Range: -4.0322
Max Act: 3.7977. Min Act: -0.1700
Data Index: 2995748 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0322. Min Range: -4.0322
Max Act: 3.7820. Min Act: -0.1700
Data Index: 6298968 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0322. Min Range: -4.0322
Max Act: 3.7664. Min Act: -0.1700
Data Index: 8609052 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0322. Min Range: -4.0322
Max Act: 3.7664. Min Act: -0.1700
Data Index: 6649588 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0322. Min Range: -4.0322
Max Act: 3.7508. Min Act: -0.1700
Data Index: 599259 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0322. Min Range: -4.0322
Max Act: 3.7351. Min Act: -0.1700
Data Index: 4637378 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0322. Min Range: -4.0322
Max Act: 3.7195. Min Act: -0.1700
Data Index: 6606009 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0322. Min Range: -4.0322
Max Act: 3.7351. Min Act: -0.1700
Data Index: 3830004 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0322. Min Range: -4.0322
Max Act: 3.7351. Min Act: -0.1700
Data Index: 2506312 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0322. Min Range: -4.0322
Max Act: 3.7195. Min Act: -0.1700
Data Index: 5084908 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19