Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1715 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6529. Min Range: -6.6529
Max Act: 6.6529. Min Act: -0.1700
Data Index: 5766739 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6529. Min Range: -6.6529
Max Act: 6.4342. Min Act: -0.1700
Data Index: 6166673 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6529. Min Range: -6.6529
Max Act: 6.4029. Min Act: -0.1700
Data Index: 6520960 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6529. Min Range: -6.6529
Max Act: 6.3404. Min Act: -0.1700
Data Index: 3396756 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6529. Min Range: -6.6529
Max Act: 6.3404. Min Act: -0.1700
Data Index: 3855948 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6529. Min Range: -6.6529
Max Act: 6.3404. Min Act: -0.1700
Data Index: 6558048 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6529. Min Range: -6.6529
Max Act: 6.3092. Min Act: -0.1700
Data Index: 4451810 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6529. Min Range: -6.6529
Max Act: 6.2154. Min Act: -0.1700
Data Index: 1251446 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6529. Min Range: -6.6529
Max Act: 6.2154. Min Act: -0.1700
Data Index: 1661404 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6529. Min Range: -6.6529
Max Act: 6.2154. Min Act: -0.1700
Data Index: 4253999 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6529. Min Range: -6.6529
Max Act: 6.1529. Min Act: -0.1700
Data Index: 3588429 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6529. Min Range: -6.6529
Max Act: 6.1217. Min Act: -0.1700
Data Index: 4098975 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6529. Min Range: -6.6529
Max Act: 6.1217. Min Act: -0.1700
Data Index: 1251445 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6529. Min Range: -6.6529
Max Act: 6.1217. Min Act: -0.1700
Data Index: 130627 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6529. Min Range: -6.6529
Max Act: 6.0904. Min Act: -0.1700
Data Index: 1347639 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6529. Min Range: -6.6529
Max Act: 6.0904. Min Act: -0.1700
Data Index: 4451811 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6529. Min Range: -6.6529
Max Act: 6.0904. Min Act: -0.1700
Data Index: 5003663 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6529. Min Range: -6.6529
Max Act: 6.0904. Min Act: -0.1700
Data Index: 8039296 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6529. Min Range: -6.6529
Max Act: 6.0592. Min Act: -0.1700
Data Index: 8121757 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6529. Min Range: -6.6529
Max Act: 6.0904. Min Act: -0.1700
Data Index: 3279067 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19