Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2130 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1880. Min Range: -5.1880
Max Act: 5.1880. Min Act: -0.1700
Data Index: 3834857 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1880. Min Range: -5.1880
Max Act: 5.0630. Min Act: -0.1700
Data Index: 3553221 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1880. Min Range: -5.1880
Max Act: 4.9692. Min Act: -0.1700
Data Index: 1078169 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1880. Min Range: -5.1880
Max Act: 4.9380. Min Act: -0.1700
Data Index: 7502307 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1880. Min Range: -5.1880
Max Act: 4.9380. Min Act: -0.1700
Data Index: 2686650 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1880. Min Range: -5.1880
Max Act: 4.9067. Min Act: -0.1700
Data Index: 2436776 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1880. Min Range: -5.1880
Max Act: 4.8755. Min Act: -0.1700
Data Index: 7584899 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1880. Min Range: -5.1880
Max Act: 4.8755. Min Act: -0.1700
Data Index: 7451813 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1880. Min Range: -5.1880
Max Act: 4.8442. Min Act: -0.1700
Data Index: 8463832 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1880. Min Range: -5.1880
Max Act: 4.8442. Min Act: -0.1700
Data Index: 4430992 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1880. Min Range: -5.1880
Max Act: 4.8442. Min Act: -0.1700
Data Index: 8075526 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1880. Min Range: -5.1880
Max Act: 4.8442. Min Act: -0.1700
Data Index: 3029321 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1880. Min Range: -5.1880
Max Act: 4.8130. Min Act: -0.1700
Data Index: 1596438 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1880. Min Range: -5.1880
Max Act: 4.7817. Min Act: -0.1700
Data Index: 3596012 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1880. Min Range: -5.1880
Max Act: 4.7817. Min Act: -0.1700
Data Index: 4520271 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1880. Min Range: -5.1880
Max Act: 4.7817. Min Act: -0.1700
Data Index: 4930889 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1880. Min Range: -5.1880
Max Act: 4.7505. Min Act: -0.1700
Data Index: 2813106 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1880. Min Range: -5.1880
Max Act: 4.7505. Min Act: -0.1700
Data Index: 5568351 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1880. Min Range: -5.1880
Max Act: 4.7505. Min Act: -0.1700
Data Index: 4195030 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1880. Min Range: -5.1880
Max Act: 4.7192. Min Act: -0.1700
Data Index: 767482 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19