Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5688 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1894. Min Range: -7.1894
Max Act: 7.1894. Min Act: -0.1700
Data Index: 5348152 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1894. Min Range: -7.1894
Max Act: 7.1269. Min Act: -0.1700
Data Index: 6393740 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1894. Min Range: -7.1894
Max Act: 7.0957. Min Act: -0.1700
Data Index: 5357120 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1894. Min Range: -7.1894
Max Act: 7.0644. Min Act: -0.1700
Data Index: 7163989 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1894. Min Range: -7.1894
Max Act: 7.0644. Min Act: -0.1700
Data Index: 6296884 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1894. Min Range: -7.1894
Max Act: 7.0644. Min Act: -0.1700
Data Index: 7361561 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1894. Min Range: -7.1894
Max Act: 7.0332. Min Act: -0.1700
Data Index: 4273232 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1894. Min Range: -7.1894
Max Act: 6.9707. Min Act: -0.1700
Data Index: 1347458 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1894. Min Range: -7.1894
Max Act: 6.9082. Min Act: -0.1700
Data Index: 4719730 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1894. Min Range: -7.1894
Max Act: 6.9082. Min Act: -0.1700
Data Index: 3217555 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1894. Min Range: -7.1894
Max Act: 6.8769. Min Act: -0.1700
Data Index: 8607392 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1894. Min Range: -7.1894
Max Act: 6.8457. Min Act: -0.1700
Data Index: 5134929 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1894. Min Range: -7.1894
Max Act: 6.8457. Min Act: -0.1700
Data Index: 7340527 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1894. Min Range: -7.1894
Max Act: 6.8144. Min Act: -0.1700
Data Index: 499515 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1894. Min Range: -7.1894
Max Act: 6.7519. Min Act: -0.1700
Data Index: 8216203 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1894. Min Range: -7.1894
Max Act: 6.7519. Min Act: -0.1700
Data Index: 6515353 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1894. Min Range: -7.1894
Max Act: 6.6894. Min Act: -0.1700
Data Index: 4080334 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1894. Min Range: -7.1894
Max Act: 6.6894. Min Act: -0.1700
Data Index: 364994 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1894. Min Range: -7.1894
Max Act: 6.6894. Min Act: -0.1700
Data Index: 7567512 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1894. Min Range: -7.1894
Max Act: 6.6582. Min Act: -0.1700
Data Index: 5043063 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #19