Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3694 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3651. Min Range: -3.3651
Max Act: 3.3651. Min Act: -0.1700
Data Index: 5325998 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3651. Min Range: -3.3651
Max Act: 3.3651. Min Act: -0.1700
Data Index: 6918736 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3651. Min Range: -3.3651
Max Act: 3.3651. Min Act: -0.1700
Data Index: 8510435 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3651. Min Range: -3.3651
Max Act: 3.3494. Min Act: -0.1700
Data Index: 5638077 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3651. Min Range: -3.3651
Max Act: 3.3337. Min Act: -0.1700
Data Index: 6700190 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3651. Min Range: -3.3651
Max Act: 3.3337. Min Act: -0.1700
Data Index: 6043050 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3651. Min Range: -3.3651
Max Act: 3.3180. Min Act: -0.1700
Data Index: 328119 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3651. Min Range: -3.3651
Max Act: 3.3023. Min Act: -0.1700
Data Index: 5798555 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3651. Min Range: -3.3651
Max Act: 3.3180. Min Act: -0.1700
Data Index: 3144697 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3651. Min Range: -3.3651
Max Act: 3.3023. Min Act: -0.1700
Data Index: 1187072 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3651. Min Range: -3.3651
Max Act: 3.3023. Min Act: -0.1700
Data Index: 665647 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3651. Min Range: -3.3651
Max Act: 3.2866. Min Act: -0.1700
Data Index: 4517993 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3651. Min Range: -3.3651
Max Act: 3.2866. Min Act: -0.1700
Data Index: 8455849 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3651. Min Range: -3.3651
Max Act: 3.2709. Min Act: -0.1700
Data Index: 1660336 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3651. Min Range: -3.3651
Max Act: 3.2866. Min Act: -0.1700
Data Index: 7422341 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3651. Min Range: -3.3651
Max Act: 3.2709. Min Act: -0.1700
Data Index: 3596918 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3651. Min Range: -3.3651
Max Act: 3.2709. Min Act: -0.1700
Data Index: 964049 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3651. Min Range: -3.3651
Max Act: 3.2709. Min Act: -0.1700
Data Index: 2442327 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3651. Min Range: -3.3651
Max Act: 3.2709. Min Act: -0.1700
Data Index: 2670533 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3651. Min Range: -3.3651
Max Act: 3.2709. Min Act: -0.1700
Data Index: 7348496 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19