Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3426 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7701. Min Range: -3.7701
Max Act: 3.7701. Min Act: -0.1700
Data Index: 5423519 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7701. Min Range: -3.7701
Max Act: 3.7701. Min Act: -0.1700
Data Index: 5583890 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7701. Min Range: -3.7701
Max Act: 3.7389. Min Act: -0.1700
Data Index: 3070013 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7701. Min Range: -3.7701
Max Act: 3.7389. Min Act: -0.1700
Data Index: 7735887 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7701. Min Range: -3.7701
Max Act: 3.7389. Min Act: -0.1700
Data Index: 4569652 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7701. Min Range: -3.7701
Max Act: 3.7389. Min Act: -0.1700
Data Index: 5423520 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7701. Min Range: -3.7701
Max Act: 3.7389. Min Act: -0.1700
Data Index: 291132 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7701. Min Range: -3.7701
Max Act: 3.7389. Min Act: -0.1700
Data Index: 1258089 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7701. Min Range: -3.7701
Max Act: 3.7389. Min Act: -0.1700
Data Index: 7608775 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7701. Min Range: -3.7701
Max Act: 3.7076. Min Act: -0.1700
Data Index: 2986936 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7701. Min Range: -3.7701
Max Act: 3.7076. Min Act: -0.1700
Data Index: 339083 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7701. Min Range: -3.7701
Max Act: 3.7076. Min Act: -0.1700
Data Index: 503434 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7701. Min Range: -3.7701
Max Act: 3.6763. Min Act: -0.1700
Data Index: 7276246 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7701. Min Range: -3.7701
Max Act: 3.6763. Min Act: -0.1700
Data Index: 1274482 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7701. Min Range: -3.7701
Max Act: 3.6763. Min Act: -0.1700
Data Index: 339082 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7701. Min Range: -3.7701
Max Act: 3.6763. Min Act: -0.1700
Data Index: 1315937 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7701. Min Range: -3.7701
Max Act: 3.6763. Min Act: -0.1700
Data Index: 1864768 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7701. Min Range: -3.7701
Max Act: 3.6450. Min Act: -0.1700
Data Index: 4054763 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7701. Min Range: -3.7701
Max Act: 3.6450. Min Act: -0.1700
Data Index: 4468219 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7701. Min Range: -3.7701
Max Act: 3.6450. Min Act: -0.1700
Data Index: 561531 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19