Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 660 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0581. Min Range: -5.0581
Max Act: 5.0581. Min Act: -0.1700
Data Index: 7732705 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0581. Min Range: -5.0581
Max Act: 5.0269. Min Act: -0.1700
Data Index: 7384569 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0581. Min Range: -5.0581
Max Act: 4.9956. Min Act: -0.1700
Data Index: 8126869 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0581. Min Range: -5.0581
Max Act: 4.9956. Min Act: -0.1700
Data Index: 5101498 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0581. Min Range: -5.0581
Max Act: 4.9956. Min Act: -0.1700
Data Index: 2991204 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0581. Min Range: -5.0581
Max Act: 4.9956. Min Act: -0.1700
Data Index: 3617611 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0581. Min Range: -5.0581
Max Act: 4.9644. Min Act: -0.1700
Data Index: 3333544 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0581. Min Range: -5.0581
Max Act: 4.9644. Min Act: -0.1700
Data Index: 6762286 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0581. Min Range: -5.0581
Max Act: 4.9644. Min Act: -0.1700
Data Index: 4917439 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0581. Min Range: -5.0581
Max Act: 4.9331. Min Act: -0.1700
Data Index: 1174903 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0581. Min Range: -5.0581
Max Act: 4.9331. Min Act: -0.1700
Data Index: 6753286 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0581. Min Range: -5.0581
Max Act: 4.9331. Min Act: -0.1700
Data Index: 995365 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0581. Min Range: -5.0581
Max Act: 4.9331. Min Act: -0.1700
Data Index: 4436438 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0581. Min Range: -5.0581
Max Act: 4.9331. Min Act: -0.1700
Data Index: 283111 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0581. Min Range: -5.0581
Max Act: 4.9331. Min Act: -0.1700
Data Index: 865418 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0581. Min Range: -5.0581
Max Act: 4.9331. Min Act: -0.1700
Data Index: 2848178 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0581. Min Range: -5.0581
Max Act: 4.9019. Min Act: -0.1700
Data Index: 3466531 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0581. Min Range: -5.0581
Max Act: 4.9019. Min Act: -0.1700
Data Index: 4479460 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0581. Min Range: -5.0581
Max Act: 4.9019. Min Act: -0.1700
Data Index: 2247489 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0581. Min Range: -5.0581
Max Act: 4.9019. Min Act: -0.1700
Data Index: 5481889 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19