Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1006 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3008. Min Range: -2.3008
Max Act: 2.3008. Min Act: -0.1700
Data Index: 345040 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3008. Min Range: -2.3008
Max Act: 2.2843. Min Act: -0.1700
Data Index: 6380493 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3008. Min Range: -2.3008
Max Act: 2.2678. Min Act: -0.1700
Data Index: 6372160 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3008. Min Range: -2.3008
Max Act: 2.2513. Min Act: -0.1700
Data Index: 6674358 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3008. Min Range: -2.3008
Max Act: 2.2843. Min Act: -0.1700
Data Index: 8459722 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3008. Min Range: -2.3008
Max Act: 2.2513. Min Act: -0.1700
Data Index: 8721650 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3008. Min Range: -2.3008
Max Act: 2.2348. Min Act: -0.1700
Data Index: 7113746 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3008. Min Range: -2.3008
Max Act: 2.2513. Min Act: -0.1700
Data Index: 345041 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3008. Min Range: -2.3008
Max Act: 2.2182. Min Act: -0.1700
Data Index: 5262198 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3008. Min Range: -2.3008
Max Act: 2.2182. Min Act: -0.1700
Data Index: 4736027 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3008. Min Range: -2.3008
Max Act: 2.2017. Min Act: -0.1700
Data Index: 7507341 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3008. Min Range: -2.3008
Max Act: 2.2017. Min Act: -0.1700
Data Index: 8717974 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3008. Min Range: -2.3008
Max Act: 2.2017. Min Act: -0.1700
Data Index: 2800343 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3008. Min Range: -2.3008
Max Act: 2.2017. Min Act: -0.1700
Data Index: 7319522 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3008. Min Range: -2.3008
Max Act: 2.2017. Min Act: -0.1700
Data Index: 3263714 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3008. Min Range: -2.3008
Max Act: 2.2017. Min Act: -0.1700
Data Index: 7903228 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3008. Min Range: -2.3008
Max Act: 2.1684. Min Act: -0.1700
Data Index: 3272109 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3008. Min Range: -2.3008
Max Act: 2.1684. Min Act: -0.1700
Data Index: 7945412 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3008. Min Range: -2.3008
Max Act: 2.1851. Min Act: -0.1700
Data Index: 999861 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3008. Min Range: -2.3008
Max Act: 2.1851. Min Act: -0.1700
Data Index: 3022655 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19