Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4012 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3959. Min Range: -6.3959
Max Act: 6.3959. Min Act: -0.1700
Data Index: 5330058 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3959. Min Range: -6.3959
Max Act: 6.3646. Min Act: -0.1700
Data Index: 8542130 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3959. Min Range: -6.3959
Max Act: 6.3646. Min Act: -0.1700
Data Index: 5430993 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3959. Min Range: -6.3959
Max Act: 6.3334. Min Act: -0.1700
Data Index: 8355089 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3959. Min Range: -6.3959
Max Act: 6.3334. Min Act: -0.1700
Data Index: 354556 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3959. Min Range: -6.3959
Max Act: 6.3334. Min Act: -0.1700
Data Index: 3611661 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3959. Min Range: -6.3959
Max Act: 6.3334. Min Act: -0.1700
Data Index: 1901612 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3959. Min Range: -6.3959
Max Act: 6.3334. Min Act: -0.1700
Data Index: 1825440 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3959. Min Range: -6.3959
Max Act: 6.2709. Min Act: -0.1700
Data Index: 3859146 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3959. Min Range: -6.3959
Max Act: 6.2396. Min Act: -0.1700
Data Index: 5685460 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3959. Min Range: -6.3959
Max Act: 6.2709. Min Act: -0.1700
Data Index: 6957446 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3959. Min Range: -6.3959
Max Act: 6.2084. Min Act: -0.1700
Data Index: 2132964 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3959. Min Range: -6.3959
Max Act: 6.2084. Min Act: -0.1700
Data Index: 8370694 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3959. Min Range: -6.3959
Max Act: 6.1459. Min Act: -0.1700
Data Index: 4373080 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3959. Min Range: -6.3959
Max Act: 6.1459. Min Act: -0.1700
Data Index: 8370695 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3959. Min Range: -6.3959
Max Act: 6.1459. Min Act: -0.1700
Data Index: 6231255 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3959. Min Range: -6.3959
Max Act: 6.1146. Min Act: -0.1700
Data Index: 163473 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3959. Min Range: -6.3959
Max Act: 6.1146. Min Act: -0.1700
Data Index: 1614960 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3959. Min Range: -6.3959
Max Act: 6.0834. Min Act: -0.1700
Data Index: 8326002 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3959. Min Range: -6.3959
Max Act: 6.0521. Min Act: -0.1700
Data Index: 4650849 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #19