Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 31 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7630. Min Range: -5.7630
Max Act: 5.7630. Min Act: -0.1700
Data Index: 691848 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7630. Min Range: -5.7630
Max Act: 5.4192. Min Act: -0.1700
Data Index: 3656267 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7630. Min Range: -5.7630
Max Act: 5.3880. Min Act: -0.1700
Data Index: 5263882 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7630. Min Range: -5.7630
Max Act: 5.3567. Min Act: -0.1700
Data Index: 3843410 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7630. Min Range: -5.7630
Max Act: 5.3567. Min Act: -0.1700
Data Index: 1382419 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7630. Min Range: -5.7630
Max Act: 5.2630. Min Act: -0.1700
Data Index: 2513018 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7630. Min Range: -5.7630
Max Act: 5.2005. Min Act: -0.1700
Data Index: 5780560 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7630. Min Range: -5.7630
Max Act: 5.2005. Min Act: -0.1700
Data Index: 3065103 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7630. Min Range: -5.7630
Max Act: 5.1692. Min Act: -0.1700
Data Index: 8534394 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7630. Min Range: -5.7630
Max Act: 5.1692. Min Act: -0.1700
Data Index: 64392 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7630. Min Range: -5.7630
Max Act: 5.1380. Min Act: -0.1700
Data Index: 8675529 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7630. Min Range: -5.7630
Max Act: 5.1380. Min Act: -0.1700
Data Index: 8403228 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7630. Min Range: -5.7630
Max Act: 5.1380. Min Act: -0.1700
Data Index: 644720 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7630. Min Range: -5.7630
Max Act: 5.0755. Min Act: -0.1700
Data Index: 4766856 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7630. Min Range: -5.7630
Max Act: 5.1380. Min Act: -0.1700
Data Index: 3620304 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7630. Min Range: -5.7630
Max Act: 5.1067. Min Act: -0.1700
Data Index: 2073615 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7630. Min Range: -5.7630
Max Act: 5.1067. Min Act: -0.1700
Data Index: 997573 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7630. Min Range: -5.7630
Max Act: 5.0755. Min Act: -0.1700
Data Index: 5780561 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7630. Min Range: -5.7630
Max Act: 5.0755. Min Act: -0.1700
Data Index: 5974442 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7630. Min Range: -5.7630
Max Act: 5.0755. Min Act: -0.1700
Data Index: 1575553 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19