Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3961 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1940. Min Range: -6.1940
Max Act: 6.1940. Min Act: -0.1700
Data Index: 627536 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1940. Min Range: -6.1940
Max Act: 6.1003. Min Act: -0.1700
Data Index: 1430757 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1940. Min Range: -6.1940
Max Act: 6.0378. Min Act: -0.1700
Data Index: 7459698 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1940. Min Range: -6.1940
Max Act: 6.0065. Min Act: -0.1700
Data Index: 5349963 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1940. Min Range: -6.1940
Max Act: 6.0065. Min Act: -0.1700
Data Index: 6138108 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1940. Min Range: -6.1940
Max Act: 5.9440. Min Act: -0.1700
Data Index: 2691363 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1940. Min Range: -6.1940
Max Act: 5.9128. Min Act: -0.1700
Data Index: 3156507 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1940. Min Range: -6.1940
Max Act: 5.9128. Min Act: -0.1700
Data Index: 7279073 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1940. Min Range: -6.1940
Max Act: 5.8815. Min Act: -0.1700
Data Index: 8613927 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1940. Min Range: -6.1940
Max Act: 5.8503. Min Act: -0.1700
Data Index: 1005967 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1940. Min Range: -6.1940
Max Act: 5.7878. Min Act: -0.1700
Data Index: 447221 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1940. Min Range: -6.1940
Max Act: 5.8190. Min Act: -0.1700
Data Index: 1998604 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1940. Min Range: -6.1940
Max Act: 5.7878. Min Act: -0.1700
Data Index: 4377063 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1940. Min Range: -6.1940
Max Act: 5.8190. Min Act: -0.1700
Data Index: 372679 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1940. Min Range: -6.1940
Max Act: 5.7565. Min Act: -0.1700
Data Index: 7767270 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1940. Min Range: -6.1940
Max Act: 5.7565. Min Act: -0.1700
Data Index: 8205120 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1940. Min Range: -6.1940
Max Act: 5.7565. Min Act: -0.1700
Data Index: 4800728 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1940. Min Range: -6.1940
Max Act: 5.7565. Min Act: -0.1700
Data Index: 6234765 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1940. Min Range: -6.1940
Max Act: 5.7565. Min Act: -0.1700
Data Index: 4993728 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1940. Min Range: -6.1940
Max Act: 5.7253. Min Act: -0.1700
Data Index: 813239 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19