Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3541 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.7852. Min Range: -10.7852
Max Act: 10.7852. Min Act: -0.1700
Data Index: 6115119 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.7852. Min Range: -10.7852
Max Act: 10.7227. Min Act: -0.1700
Data Index: 4829906 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.7852. Min Range: -10.7852
Max Act: 10.5352. Min Act: -0.1700
Data Index: 2826984 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.7852. Min Range: -10.7852
Max Act: 10.4102. Min Act: -0.1700
Data Index: 7403506 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.7852. Min Range: -10.7852
Max Act: 10.2852. Min Act: -0.1700
Data Index: 784366 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.7852. Min Range: -10.7852
Max Act: 10.1602. Min Act: -0.1700
Data Index: 2984920 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.7852. Min Range: -10.7852
Max Act: 9.9727. Min Act: -0.1700
Data Index: 8493114 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.7852. Min Range: -10.7852
Max Act: 9.9727. Min Act: -0.1700
Data Index: 1351063 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.7852. Min Range: -10.7852
Max Act: 9.9102. Min Act: -0.1700
Data Index: 815089 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.7852. Min Range: -10.7852
Max Act: 9.9102. Min Act: -0.1700
Data Index: 3904118 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.7852. Min Range: -10.7852
Max Act: 9.8477. Min Act: -0.1700
Data Index: 2130317 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.7852. Min Range: -10.7852
Max Act: 9.8477. Min Act: -0.1700
Data Index: 7226854 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.7852. Min Range: -10.7852
Max Act: 9.8477. Min Act: -0.1700
Data Index: 369244 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.7852. Min Range: -10.7852
Max Act: 9.7852. Min Act: -0.1700
Data Index: 2984899 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.7852. Min Range: -10.7852
Max Act: 9.7852. Min Act: -0.1700
Data Index: 2977755 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.7852. Min Range: -10.7852
Max Act: 9.7852. Min Act: -0.1700
Data Index: 6115157 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.7852. Min Range: -10.7852
Max Act: 9.7852. Min Act: -0.1700
Data Index: 3620369 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.7852. Min Range: -10.7852
Max Act: 9.7227. Min Act: -0.1700
Data Index: 626687 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.7852. Min Range: -10.7852
Max Act: 9.7227. Min Act: -0.1700
Data Index: 4894513 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.7852. Min Range: -10.7852
Max Act: 9.7227. Min Act: -0.1700
Data Index: 4286431 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19