Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2634 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9665. Min Range: -4.9665
Max Act: 4.9665. Min Act: -0.1700
Data Index: 597460 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9665. Min Range: -4.9665
Max Act: 4.8728. Min Act: -0.1700
Data Index: 867019 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9665. Min Range: -4.9665
Max Act: 4.8103. Min Act: -0.1700
Data Index: 3605272 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9665. Min Range: -4.9665
Max Act: 4.7790. Min Act: -0.1700
Data Index: 3868413 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9665. Min Range: -4.9665
Max Act: 4.7165. Min Act: -0.1700
Data Index: 2974697 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9665. Min Range: -4.9665
Max Act: 4.7165. Min Act: -0.1700
Data Index: 7693348 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9665. Min Range: -4.9665
Max Act: 4.7165. Min Act: -0.1700
Data Index: 3822707 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9665. Min Range: -4.9665
Max Act: 4.6853. Min Act: -0.1700
Data Index: 2001188 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9665. Min Range: -4.9665
Max Act: 4.6853. Min Act: -0.1700
Data Index: 5322780 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9665. Min Range: -4.9665
Max Act: 4.6853. Min Act: -0.1700
Data Index: 6908406 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9665. Min Range: -4.9665
Max Act: 4.6228. Min Act: -0.1700
Data Index: 3601610 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9665. Min Range: -4.9665
Max Act: 4.6228. Min Act: -0.1700
Data Index: 6765496 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9665. Min Range: -4.9665
Max Act: 4.6228. Min Act: -0.1700
Data Index: 8556891 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9665. Min Range: -4.9665
Max Act: 4.5915. Min Act: -0.1700
Data Index: 5068410 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9665. Min Range: -4.9665
Max Act: 4.6228. Min Act: -0.1700
Data Index: 5225792 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9665. Min Range: -4.9665
Max Act: 4.5915. Min Act: -0.1700
Data Index: 7181107 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9665. Min Range: -4.9665
Max Act: 4.5915. Min Act: -0.1700
Data Index: 2744336 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9665. Min Range: -4.9665
Max Act: 4.5915. Min Act: -0.1700
Data Index: 7692441 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9665. Min Range: -4.9665
Max Act: 4.5603. Min Act: -0.1700
Data Index: 7206768 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9665. Min Range: -4.9665
Max Act: 4.5603. Min Act: -0.1700
Data Index: 5274089 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19