Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1438 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1665. Min Range: -6.1665
Max Act: 6.1665. Min Act: -0.1700
Data Index: 4852861 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1665. Min Range: -6.1665
Max Act: 6.0415. Min Act: -0.1700
Data Index: 1731959 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1665. Min Range: -6.1665
Max Act: 5.9477. Min Act: -0.1700
Data Index: 8279298 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1665. Min Range: -6.1665
Max Act: 5.7602. Min Act: -0.1700
Data Index: 5486016 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1665. Min Range: -6.1665
Max Act: 5.7290. Min Act: -0.1700
Data Index: 1926882 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1665. Min Range: -6.1665
Max Act: 5.7290. Min Act: -0.1700
Data Index: 6656421 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1665. Min Range: -6.1665
Max Act: 5.7290. Min Act: -0.1700
Data Index: 8534972 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1665. Min Range: -6.1665
Max Act: 5.6665. Min Act: -0.1700
Data Index: 4751160 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1665. Min Range: -6.1665
Max Act: 5.6352. Min Act: -0.1700
Data Index: 8671400 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1665. Min Range: -6.1665
Max Act: 5.6352. Min Act: -0.1700
Data Index: 6667265 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1665. Min Range: -6.1665
Max Act: 5.6352. Min Act: -0.1700
Data Index: 6074174 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1665. Min Range: -6.1665
Max Act: 5.6040. Min Act: -0.1700
Data Index: 6336059 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1665. Min Range: -6.1665
Max Act: 5.6352. Min Act: -0.1700
Data Index: 4781706 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1665. Min Range: -6.1665
Max Act: 5.5727. Min Act: -0.1700
Data Index: 3589392 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1665. Min Range: -6.1665
Max Act: 5.5415. Min Act: -0.1700
Data Index: 3093638 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1665. Min Range: -6.1665
Max Act: 5.5415. Min Act: -0.1700
Data Index: 1781464 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1665. Min Range: -6.1665
Max Act: 5.5102. Min Act: -0.1700
Data Index: 2022182 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1665. Min Range: -6.1665
Max Act: 5.5102. Min Act: -0.1700
Data Index: 3839433 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1665. Min Range: -6.1665
Max Act: 5.5102. Min Act: -0.1700
Data Index: 4427585 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1665. Min Range: -6.1665
Max Act: 5.5102. Min Act: -0.1700
Data Index: 5052476 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19