Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1071 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0950. Min Range: -9.0950
Max Act: 9.0950. Min Act: -0.1700
Data Index: 7603208 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0950. Min Range: -9.0950
Max Act: 8.9075. Min Act: -0.1700
Data Index: 4777292 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0950. Min Range: -9.0950
Max Act: 8.8450. Min Act: -0.1700
Data Index: 2772009 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0950. Min Range: -9.0950
Max Act: 8.7200. Min Act: -0.1700
Data Index: 2449655 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0950. Min Range: -9.0950
Max Act: 8.6575. Min Act: -0.1700
Data Index: 3879800 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0950. Min Range: -9.0950
Max Act: 8.6575. Min Act: -0.1700
Data Index: 4621642 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0950. Min Range: -9.0950
Max Act: 8.5325. Min Act: -0.1700
Data Index: 6733988 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0950. Min Range: -9.0950
Max Act: 8.4700. Min Act: -0.1700
Data Index: 4498645 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0950. Min Range: -9.0950
Max Act: 8.4075. Min Act: -0.1700
Data Index: 3087531 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0950. Min Range: -9.0950
Max Act: 8.3450. Min Act: -0.1700
Data Index: 6879085 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0950. Min Range: -9.0950
Max Act: 8.3450. Min Act: -0.1700
Data Index: 7873089 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0950. Min Range: -9.0950
Max Act: 8.2825. Min Act: -0.1700
Data Index: 3344791 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0950. Min Range: -9.0950
Max Act: 8.2825. Min Act: -0.1700
Data Index: 6856406 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0950. Min Range: -9.0950
Max Act: 8.2825. Min Act: -0.1700
Data Index: 4842081 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0950. Min Range: -9.0950
Max Act: 8.2200. Min Act: -0.1700
Data Index: 4607061 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0950. Min Range: -9.0950
Max Act: 8.2825. Min Act: -0.1700
Data Index: 7145691 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0950. Min Range: -9.0950
Max Act: 8.2825. Min Act: -0.1700
Data Index: 1719887 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0950. Min Range: -9.0950
Max Act: 8.2825. Min Act: -0.1700
Data Index: 5660786 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0950. Min Range: -9.0950
Max Act: 8.2825. Min Act: -0.1700
Data Index: 7675220 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0950. Min Range: -9.0950
Max Act: 8.2825. Min Act: -0.1698
Data Index: 307633 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19