Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5094 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2517. Min Range: -7.2517
Max Act: 7.2517. Min Act: -0.1700
Data Index: 8635612 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2517. Min Range: -7.2517
Max Act: 7.2517. Min Act: -0.1700
Data Index: 2954698 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2517. Min Range: -7.2517
Max Act: 7.1892. Min Act: -0.1700
Data Index: 2068081 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2517. Min Range: -7.2517
Max Act: 7.1892. Min Act: -0.1700
Data Index: 4647959 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2517. Min Range: -7.2517
Max Act: 7.1267. Min Act: -0.1700
Data Index: 5893740 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2517. Min Range: -7.2517
Max Act: 7.0954. Min Act: -0.1700
Data Index: 7282160 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2517. Min Range: -7.2517
Max Act: 7.0642. Min Act: -0.1700
Data Index: 5361909 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2517. Min Range: -7.2517
Max Act: 6.9704. Min Act: -0.1700
Data Index: 4621646 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2517. Min Range: -7.2517
Max Act: 6.9079. Min Act: -0.1700
Data Index: 759125 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2517. Min Range: -7.2517
Max Act: 6.9392. Min Act: -0.1700
Data Index: 567344 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2517. Min Range: -7.2517
Max Act: 6.9392. Min Act: -0.1700
Data Index: 782360 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2517. Min Range: -7.2517
Max Act: 6.8454. Min Act: -0.1700
Data Index: 5544245 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2517. Min Range: -7.2517
Max Act: 6.8142. Min Act: -0.1700
Data Index: 5026740 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2517. Min Range: -7.2517
Max Act: 6.7829. Min Act: -0.1700
Data Index: 1291980 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2517. Min Range: -7.2517
Max Act: 6.7829. Min Act: -0.1700
Data Index: 5482417 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2517. Min Range: -7.2517
Max Act: 6.7517. Min Act: -0.1700
Data Index: 3688741 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2517. Min Range: -7.2517
Max Act: 6.7517. Min Act: -0.1700
Data Index: 1479155 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2517. Min Range: -7.2517
Max Act: 6.7204. Min Act: -0.1700
Data Index: 2406719 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2517. Min Range: -7.2517
Max Act: 6.7204. Min Act: -0.1700
Data Index: 1760432 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2517. Min Range: -7.2517
Max Act: 6.6892. Min Act: -0.1700
Data Index: 6231144 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19