Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4913 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9687. Min Range: -8.9687
Max Act: 8.9687. Min Act: -0.1700
Data Index: 118966 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9687. Min Range: -8.9687
Max Act: 8.9062. Min Act: -0.1700
Data Index: 6303044 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9687. Min Range: -8.9687
Max Act: 8.7187. Min Act: -0.1700
Data Index: 3430453 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9687. Min Range: -8.9687
Max Act: 8.5937. Min Act: -0.1700
Data Index: 8440308 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9687. Min Range: -8.9687
Max Act: 8.5312. Min Act: -0.1700
Data Index: 2952973 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9687. Min Range: -8.9687
Max Act: 8.5312. Min Act: -0.1700
Data Index: 1841393 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9687. Min Range: -8.9687
Max Act: 8.4687. Min Act: -0.1700
Data Index: 7051614 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9687. Min Range: -8.9687
Max Act: 8.4062. Min Act: -0.1700
Data Index: 4309345 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9687. Min Range: -8.9687
Max Act: 8.4687. Min Act: -0.1700
Data Index: 620760 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9687. Min Range: -8.9687
Max Act: 8.3437. Min Act: -0.1700
Data Index: 6598384 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9687. Min Range: -8.9687
Max Act: 8.2812. Min Act: -0.1700
Data Index: 5555124 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9687. Min Range: -8.9687
Max Act: 8.2812. Min Act: -0.1700
Data Index: 2432192 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9687. Min Range: -8.9687
Max Act: 8.2187. Min Act: -0.1700
Data Index: 5213840 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9687. Min Range: -8.9687
Max Act: 8.2187. Min Act: -0.1700
Data Index: 1986740 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9687. Min Range: -8.9687
Max Act: 8.2187. Min Act: -0.1700
Data Index: 953106 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9687. Min Range: -8.9687
Max Act: 8.2187. Min Act: -0.1700
Data Index: 5872676 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9687. Min Range: -8.9687
Max Act: 8.1562. Min Act: -0.1700
Data Index: 2715531 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9687. Min Range: -8.9687
Max Act: 8.1562. Min Act: -0.1700
Data Index: 302852 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9687. Min Range: -8.9687
Max Act: 8.1562. Min Act: -0.1700
Data Index: 5288616 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9687. Min Range: -8.9687
Max Act: 8.1562. Min Act: -0.1700
Data Index: 4060283 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19