Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3607 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.4353. Min Range: -1.4353
Max Act: 1.4353. Min Act: -0.1700
Data Index: 8326369 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4353. Min Range: -1.4353
Max Act: 1.4177. Min Act: -0.1700
Data Index: 1920266 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4353. Min Range: -1.4353
Max Act: 1.3736. Min Act: -0.1700
Data Index: 5647504 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4353. Min Range: -1.4353
Max Act: 1.3824. Min Act: -0.1700
Data Index: 436359 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4353. Min Range: -1.4353
Max Act: 1.3736. Min Act: -0.1700
Data Index: 7302127 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4353. Min Range: -1.4353
Max Act: 1.3736. Min Act: -0.1700
Data Index: 7091801 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4353. Min Range: -1.4353
Max Act: 1.3736. Min Act: -0.1700
Data Index: 2867744 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4353. Min Range: -1.4353
Max Act: 1.3648. Min Act: -0.1700
Data Index: 3890500 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4353. Min Range: -1.4353
Max Act: 1.3648. Min Act: -0.1700
Data Index: 5070133 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4353. Min Range: -1.4353
Max Act: 1.3560. Min Act: -0.1700
Data Index: 1811292 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4353. Min Range: -1.4353
Max Act: 1.3560. Min Act: -0.1700
Data Index: 1019895 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4353. Min Range: -1.4353
Max Act: 1.3648. Min Act: -0.1700
Data Index: 6202170 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4353. Min Range: -1.4353
Max Act: 1.3472. Min Act: -0.1700
Data Index: 1735833 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4353. Min Range: -1.4353
Max Act: 1.3383. Min Act: -0.1700
Data Index: 5429965 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4353. Min Range: -1.4353
Max Act: 1.3383. Min Act: -0.1700
Data Index: 5290228 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4353. Min Range: -1.4353
Max Act: 1.3383. Min Act: -0.1700
Data Index: 2484380 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4353. Min Range: -1.4353
Max Act: 1.3295. Min Act: -0.1700
Data Index: 5285047 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4353. Min Range: -1.4353
Max Act: 1.3383. Min Act: -0.1700
Data Index: 4144326 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4353. Min Range: -1.4353
Max Act: 1.3207. Min Act: -0.1700
Data Index: 2649381 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4353. Min Range: -1.4353
Max Act: 1.3031. Min Act: -0.1700
Data Index: 7922563 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19