Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 595 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2722. Min Range: -6.2722
Max Act: 6.2722. Min Act: -0.1700
Data Index: 5483807 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2722. Min Range: -6.2722
Max Act: 6.2410. Min Act: -0.1700
Data Index: 4242517 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2722. Min Range: -6.2722
Max Act: 6.1785. Min Act: -0.1700
Data Index: 26901 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2722. Min Range: -6.2722
Max Act: 6.1160. Min Act: -0.1700
Data Index: 870801 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2722. Min Range: -6.2722
Max Act: 6.2097. Min Act: -0.1700
Data Index: 3678483 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2722. Min Range: -6.2722
Max Act: 6.2097. Min Act: -0.1700
Data Index: 7957912 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2722. Min Range: -6.2722
Max Act: 6.1785. Min Act: -0.1700
Data Index: 3880312 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2722. Min Range: -6.2722
Max Act: 6.1472. Min Act: -0.1700
Data Index: 4242516 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2722. Min Range: -6.2722
Max Act: 6.0535. Min Act: -0.1700
Data Index: 4229455 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2722. Min Range: -6.2722
Max Act: 6.0535. Min Act: -0.1700
Data Index: 26900 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2722. Min Range: -6.2722
Max Act: 6.0222. Min Act: -0.1700
Data Index: 5107252 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2722. Min Range: -6.2722
Max Act: 5.9910. Min Act: -0.1700
Data Index: 5774715 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2722. Min Range: -6.2722
Max Act: 6.0222. Min Act: -0.1700
Data Index: 6314425 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2722. Min Range: -6.2722
Max Act: 5.9285. Min Act: -0.1700
Data Index: 1989255 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2722. Min Range: -6.2722
Max Act: 5.9597. Min Act: -0.1700
Data Index: 8530714 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2722. Min Range: -6.2722
Max Act: 5.9597. Min Act: -0.1700
Data Index: 2176009 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2722. Min Range: -6.2722
Max Act: 5.9910. Min Act: -0.1700
Data Index: 3728995 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2722. Min Range: -6.2722
Max Act: 5.9597. Min Act: -0.1700
Data Index: 5483806 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2722. Min Range: -6.2722
Max Act: 5.9597. Min Act: -0.1700
Data Index: 5915829 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2722. Min Range: -6.2722
Max Act: 5.8972. Min Act: -0.1700
Data Index: 5844291 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19