Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4620 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.4933. Min Act: -0.1700
Data Index: 1564033 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.4308. Min Act: -0.1700
Data Index: 5207480 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.4308. Min Act: -0.1700
Data Index: 5483433 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.3683. Min Act: -0.1700
Data Index: 5538574 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.3995. Min Act: -0.1700
Data Index: 1857868 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.2433. Min Act: -0.1700
Data Index: 7006105 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.2745. Min Act: -0.1700
Data Index: 704258 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.1808. Min Act: -0.1700
Data Index: 2825874 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.2120. Min Act: -0.1700
Data Index: 2564351 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.2120. Min Act: -0.1700
Data Index: 4986397 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.2120. Min Act: -0.1700
Data Index: 5696174 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.2120. Min Act: -0.1700
Data Index: 4110546 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.1808. Min Act: -0.1700
Data Index: 5362630 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.1495. Min Act: -0.1700
Data Index: 1173790 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.0870. Min Act: -0.1700
Data Index: 2020776 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.0870. Min Act: -0.1700
Data Index: 7491567 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.0870. Min Act: -0.1700
Data Index: 8172766 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.0870. Min Act: -0.1700
Data Index: 4968495 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.0558. Min Act: -0.1700
Data Index: 2192347 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4933. Min Range: -6.4933
Max Act: 6.0558. Min Act: -0.1700
Data Index: 5901469 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19