Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3662 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0102. Min Range: -6.0102
Max Act: 6.0102. Min Act: -0.1700
Data Index: 7328652 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0102. Min Range: -6.0102
Max Act: 6.0102. Min Act: -0.1700
Data Index: 2704489 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0102. Min Range: -6.0102
Max Act: 5.9164. Min Act: -0.1700
Data Index: 5844057 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0102. Min Range: -6.0102
Max Act: 5.8539. Min Act: -0.1700
Data Index: 628362 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0102. Min Range: -6.0102
Max Act: 5.8539. Min Act: -0.1700
Data Index: 619354 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0102. Min Range: -6.0102
Max Act: 5.7914. Min Act: -0.1700
Data Index: 7253970 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0102. Min Range: -6.0102
Max Act: 5.7914. Min Act: -0.1700
Data Index: 4816896 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0102. Min Range: -6.0102
Max Act: 5.7602. Min Act: -0.1700
Data Index: 6508164 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0102. Min Range: -6.0102
Max Act: 5.7289. Min Act: -0.1700
Data Index: 351868 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0102. Min Range: -6.0102
Max Act: 5.6977. Min Act: -0.1700
Data Index: 2807719 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0102. Min Range: -6.0102
Max Act: 5.7289. Min Act: -0.1700
Data Index: 5022554 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0102. Min Range: -6.0102
Max Act: 5.6977. Min Act: -0.1700
Data Index: 7117465 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0102. Min Range: -6.0102
Max Act: 5.6664. Min Act: -0.1700
Data Index: 6600837 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0102. Min Range: -6.0102
Max Act: 5.6352. Min Act: -0.1700
Data Index: 3184409 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0102. Min Range: -6.0102
Max Act: 5.6352. Min Act: -0.1700
Data Index: 809141 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0102. Min Range: -6.0102
Max Act: 5.6664. Min Act: -0.1700
Data Index: 6608709 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0102. Min Range: -6.0102
Max Act: 5.6039. Min Act: -0.1700
Data Index: 2104187 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0102. Min Range: -6.0102
Max Act: 5.6352. Min Act: -0.1700
Data Index: 2712564 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0102. Min Range: -6.0102
Max Act: 5.6039. Min Act: -0.1700
Data Index: 6880440 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0102. Min Range: -6.0102
Max Act: 5.5727. Min Act: -0.1700
Data Index: 6582200 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19