Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3355 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4745. Min Range: -8.4745
Max Act: 8.4745. Min Act: -0.1700
Data Index: 6901958 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4745. Min Range: -8.4745
Max Act: 8.2870. Min Act: -0.1700
Data Index: 3953262 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4745. Min Range: -8.4745
Max Act: 8.1620. Min Act: -0.1700
Data Index: 8417000 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4745. Min Range: -8.4745
Max Act: 8.0995. Min Act: -0.1700
Data Index: 7766940 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4745. Min Range: -8.4745
Max Act: 8.0370. Min Act: -0.1700
Data Index: 2485383 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4745. Min Range: -8.4745
Max Act: 8.0370. Min Act: -0.1700
Data Index: 7521069 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4745. Min Range: -8.4745
Max Act: 7.9745. Min Act: -0.1700
Data Index: 3497924 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4745. Min Range: -8.4745
Max Act: 7.9745. Min Act: -0.1700
Data Index: 2404065 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4745. Min Range: -8.4745
Max Act: 7.9120. Min Act: -0.1700
Data Index: 5017407 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4745. Min Range: -8.4745
Max Act: 7.9120. Min Act: -0.1700
Data Index: 3634800 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4745. Min Range: -8.4745
Max Act: 7.9120. Min Act: -0.1700
Data Index: 2565901 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4745. Min Range: -8.4745
Max Act: 7.8495. Min Act: -0.1700
Data Index: 1241109 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4745. Min Range: -8.4745
Max Act: 7.8495. Min Act: -0.1700
Data Index: 4649364 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4745. Min Range: -8.4745
Max Act: 7.7870. Min Act: -0.1700
Data Index: 5359829 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4745. Min Range: -8.4745
Max Act: 7.7870. Min Act: -0.1700
Data Index: 7541002 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4745. Min Range: -8.4745
Max Act: 7.7870. Min Act: -0.1700
Data Index: 4780655 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4745. Min Range: -8.4745
Max Act: 7.7245. Min Act: -0.1700
Data Index: 4469454 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4745. Min Range: -8.4745
Max Act: 7.7870. Min Act: -0.1700
Data Index: 5812915 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4745. Min Range: -8.4745
Max Act: 7.7245. Min Act: -0.1700
Data Index: 1712898 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4745. Min Range: -8.4745
Max Act: 7.7245. Min Act: -0.1700
Data Index: 6735600 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19