Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 158 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.1986. Min Range: -10.1986
Max Act: 10.1986. Min Act: -0.1700
Data Index: 2932326 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1986. Min Range: -10.1986
Max Act: 10.0736. Min Act: -0.1700
Data Index: 3862552 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1986. Min Range: -10.1986
Max Act: 9.8236. Min Act: -0.1700
Data Index: 7961908 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1986. Min Range: -10.1986
Max Act: 9.8236. Min Act: -0.1700
Data Index: 5989708 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1986. Min Range: -10.1986
Max Act: 9.8236. Min Act: -0.1700
Data Index: 6900921 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1986. Min Range: -10.1986
Max Act: 9.6986. Min Act: -0.1700
Data Index: 1200581 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1986. Min Range: -10.1986
Max Act: 9.8236. Min Act: -0.1700
Data Index: 7139681 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1986. Min Range: -10.1986
Max Act: 9.7611. Min Act: -0.1700
Data Index: 5711223 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1986. Min Range: -10.1986
Max Act: 9.6986. Min Act: -0.1700
Data Index: 8219226 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1986. Min Range: -10.1986
Max Act: 9.6361. Min Act: -0.1700
Data Index: 1992437 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1986. Min Range: -10.1986
Max Act: 9.5736. Min Act: -0.1700
Data Index: 8489097 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1986. Min Range: -10.1986
Max Act: 9.5736. Min Act: -0.1700
Data Index: 5620018 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1986. Min Range: -10.1986
Max Act: 9.5111. Min Act: -0.1700
Data Index: 5737658 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1986. Min Range: -10.1986
Max Act: 9.5736. Min Act: -0.1700
Data Index: 8400600 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1986. Min Range: -10.1986
Max Act: 9.4486. Min Act: -0.1700
Data Index: 1983723 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1986. Min Range: -10.1986
Max Act: 9.5736. Min Act: -0.1700
Data Index: 8503036 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1986. Min Range: -10.1986
Max Act: 9.5111. Min Act: -0.1700
Data Index: 2672254 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1986. Min Range: -10.1986
Max Act: 9.4486. Min Act: -0.1700
Data Index: 7321610 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1986. Min Range: -10.1986
Max Act: 9.5111. Min Act: -0.1700
Data Index: 406308 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1986. Min Range: -10.1986
Max Act: 9.4486. Min Act: -0.1700
Data Index: 3398222 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19