Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1569 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6781. Min Range: -8.6781
Max Act: 8.6781. Min Act: -0.1700
Data Index: 8739154 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6781. Min Range: -8.6781
Max Act: 8.3656. Min Act: -0.1700
Data Index: 121240 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6781. Min Range: -8.6781
Max Act: 8.3031. Min Act: -0.1700
Data Index: 1615045 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6781. Min Range: -8.6781
Max Act: 8.3031. Min Act: -0.1700
Data Index: 2755830 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6781. Min Range: -8.6781
Max Act: 8.2406. Min Act: -0.1700
Data Index: 1003085 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6781. Min Range: -8.6781
Max Act: 8.1156. Min Act: -0.1700
Data Index: 6281007 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6781. Min Range: -8.6781
Max Act: 8.1156. Min Act: -0.1700
Data Index: 935774 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6781. Min Range: -8.6781
Max Act: 8.1156. Min Act: -0.1700
Data Index: 4921750 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6781. Min Range: -8.6781
Max Act: 8.0531. Min Act: -0.1700
Data Index: 2126666 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6781. Min Range: -8.6781
Max Act: 8.0531. Min Act: -0.1700
Data Index: 5536032 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6781. Min Range: -8.6781
Max Act: 8.0531. Min Act: -0.1700
Data Index: 6130070 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6781. Min Range: -8.6781
Max Act: 8.1156. Min Act: -0.1700
Data Index: 1602606 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6781. Min Range: -8.6781
Max Act: 8.0531. Min Act: -0.1700
Data Index: 7612885 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6781. Min Range: -8.6781
Max Act: 7.9906. Min Act: -0.1700
Data Index: 4114503 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6781. Min Range: -8.6781
Max Act: 7.9906. Min Act: -0.1700
Data Index: 8785683 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6781. Min Range: -8.6781
Max Act: 7.9593. Min Act: -0.1700
Data Index: 1921875 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6781. Min Range: -8.6781
Max Act: 7.8968. Min Act: -0.1700
Data Index: 44044 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6781. Min Range: -8.6781
Max Act: 7.8968. Min Act: -0.1700
Data Index: 4315687 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6781. Min Range: -8.6781
Max Act: 7.9281. Min Act: -0.1700
Data Index: 3459916 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6781. Min Range: -8.6781
Max Act: 7.8968. Min Act: -0.1700
Data Index: 8167895 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19