Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1819 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2815. Min Range: -7.2815
Max Act: 7.2815. Min Act: -0.1700
Data Index: 6571433 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2815. Min Range: -7.2815
Max Act: 7.1565. Min Act: -0.1700
Data Index: 893993 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2815. Min Range: -7.2815
Max Act: 7.1565. Min Act: -0.1700
Data Index: 1781066 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2815. Min Range: -7.2815
Max Act: 7.1253. Min Act: -0.1700
Data Index: 130125 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2815. Min Range: -7.2815
Max Act: 7.1253. Min Act: -0.1700
Data Index: 4117969 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2815. Min Range: -7.2815
Max Act: 6.9690. Min Act: -0.1700
Data Index: 3705124 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2815. Min Range: -7.2815
Max Act: 6.9378. Min Act: -0.1700
Data Index: 8211099 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2815. Min Range: -7.2815
Max Act: 6.9065. Min Act: -0.1700
Data Index: 2099180 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2815. Min Range: -7.2815
Max Act: 6.9065. Min Act: -0.1700
Data Index: 4839087 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2815. Min Range: -7.2815
Max Act: 6.9065. Min Act: -0.1700
Data Index: 6731967 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2815. Min Range: -7.2815
Max Act: 6.8440. Min Act: -0.1700
Data Index: 2300769 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2815. Min Range: -7.2815
Max Act: 6.8753. Min Act: -0.1700
Data Index: 3514374 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2815. Min Range: -7.2815
Max Act: 6.8440. Min Act: -0.1700
Data Index: 643679 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2815. Min Range: -7.2815
Max Act: 6.8753. Min Act: -0.1700
Data Index: 945401 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2815. Min Range: -7.2815
Max Act: 6.8440. Min Act: -0.1700
Data Index: 1022655 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2815. Min Range: -7.2815
Max Act: 6.8440. Min Act: -0.1700
Data Index: 4958348 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2815. Min Range: -7.2815
Max Act: 6.8128. Min Act: -0.1700
Data Index: 7050580 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2815. Min Range: -7.2815
Max Act: 6.8128. Min Act: -0.1700
Data Index: 59326 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2815. Min Range: -7.2815
Max Act: 6.7815. Min Act: -0.1700
Data Index: 3210670 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2815. Min Range: -7.2815
Max Act: 6.8128. Min Act: -0.1700
Data Index: 8307595 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19