Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2883 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4184. Min Range: -3.4184
Max Act: 3.4184. Min Act: -0.1700
Data Index: 5582733 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4184. Min Range: -3.4184
Max Act: 3.3871. Min Act: -0.1700
Data Index: 5842422 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4184. Min Range: -3.4184
Max Act: 3.3086. Min Act: -0.1700
Data Index: 1126998 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4184. Min Range: -3.4184
Max Act: 3.2929. Min Act: -0.1700
Data Index: 5644279 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4184. Min Range: -3.4184
Max Act: 3.2929. Min Act: -0.1700
Data Index: 808368 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4184. Min Range: -3.4184
Max Act: 3.2772. Min Act: -0.1700
Data Index: 3179272 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4184. Min Range: -3.4184
Max Act: 3.2772. Min Act: -0.1700
Data Index: 4729782 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4184. Min Range: -3.4184
Max Act: 3.2615. Min Act: -0.1700
Data Index: 6407699 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4184. Min Range: -3.4184
Max Act: 3.2458. Min Act: -0.1700
Data Index: 3670622 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4184. Min Range: -3.4184
Max Act: 3.2301. Min Act: -0.1700
Data Index: 5799550 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4184. Min Range: -3.4184
Max Act: 3.2144. Min Act: -0.1700
Data Index: 7220086 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4184. Min Range: -3.4184
Max Act: 3.1986. Min Act: -0.1700
Data Index: 6174791 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4184. Min Range: -3.4184
Max Act: 3.1986. Min Act: -0.1700
Data Index: 3060511 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4184. Min Range: -3.4184
Max Act: 3.1672. Min Act: -0.1700
Data Index: 8439052 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4184. Min Range: -3.4184
Max Act: 3.1514. Min Act: -0.1700
Data Index: 4000345 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4184. Min Range: -3.4184
Max Act: 3.1514. Min Act: -0.1700
Data Index: 8437750 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4184. Min Range: -3.4184
Max Act: 3.1357. Min Act: -0.1700
Data Index: 7685178 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4184. Min Range: -3.4184
Max Act: 3.1514. Min Act: -0.1700
Data Index: 5905438 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4184. Min Range: -3.4184
Max Act: 3.1357. Min Act: -0.1700
Data Index: 816558 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4184. Min Range: -3.4184
Max Act: 3.1514. Min Act: -0.1700
Data Index: 4119557 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #19