Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4598 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2924. Min Range: -3.2924
Max Act: 3.2924. Min Act: -0.1700
Data Index: 8739538 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2924. Min Range: -3.2924
Max Act: 3.2767. Min Act: -0.1700
Data Index: 687738 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2924. Min Range: -3.2924
Max Act: 3.2610. Min Act: -0.1700
Data Index: 2060059 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2924. Min Range: -3.2924
Max Act: 3.2453. Min Act: -0.1700
Data Index: 2166188 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2924. Min Range: -3.2924
Max Act: 3.2453. Min Act: -0.1700
Data Index: 134058 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2924. Min Range: -3.2924
Max Act: 3.2453. Min Act: -0.1700
Data Index: 5091327 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2924. Min Range: -3.2924
Max Act: 3.2296. Min Act: -0.1700
Data Index: 5581855 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2924. Min Range: -3.2924
Max Act: 3.1667. Min Act: -0.1700
Data Index: 6531220 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2924. Min Range: -3.2924
Max Act: 3.1667. Min Act: -0.1700
Data Index: 8828773 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2924. Min Range: -3.2924
Max Act: 3.1509. Min Act: -0.1700
Data Index: 7379990 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2924. Min Range: -3.2924
Max Act: 3.1352. Min Act: -0.1700
Data Index: 8820121 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2924. Min Range: -3.2924
Max Act: 3.1352. Min Act: -0.1700
Data Index: 6954889 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2924. Min Range: -3.2924
Max Act: 3.1352. Min Act: -0.1700
Data Index: 5537010 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2924. Min Range: -3.2924
Max Act: 3.1509. Min Act: -0.1700
Data Index: 5285607 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2924. Min Range: -3.2924
Max Act: 3.1195. Min Act: -0.1700
Data Index: 4973843 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2924. Min Range: -3.2924
Max Act: 3.1037. Min Act: -0.1700
Data Index: 2023887 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2924. Min Range: -3.2924
Max Act: 3.1037. Min Act: -0.1700
Data Index: 3897308 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2924. Min Range: -3.2924
Max Act: 3.0879. Min Act: -0.1700
Data Index: 8061083 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2924. Min Range: -3.2924
Max Act: 3.1037. Min Act: -0.1700
Data Index: 3793450 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2924. Min Range: -3.2924
Max Act: 3.1037. Min Act: -0.1700
Data Index: 2790464 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19