Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 817 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.7117. Min Act: -0.1700
Data Index: 8671209 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.6805. Min Act: -0.1700
Data Index: 7471696 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.6492. Min Act: -0.1700
Data Index: 3744377 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.6180. Min Act: -0.1700
Data Index: 1378177 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.5867. Min Act: -0.1700
Data Index: 2128839 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.5555. Min Act: -0.1700
Data Index: 119139 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.5555. Min Act: -0.1700
Data Index: 6616303 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.5555. Min Act: -0.1700
Data Index: 1223913 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.5555. Min Act: -0.1699
Data Index: 1716489 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.5555. Min Act: -0.1700
Data Index: 1223430 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.5555. Min Act: -0.1700
Data Index: 1654149 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.5555. Min Act: -0.1700
Data Index: 813733 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.5242. Min Act: -0.1700
Data Index: 8066859 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.5242. Min Act: -0.1700
Data Index: 6181265 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.5242. Min Act: -0.1699
Data Index: 5918165 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.4930. Min Act: -0.1700
Data Index: 4860641 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.4930. Min Act: -0.1700
Data Index: 5170969 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.4930. Min Act: -0.1700
Data Index: 1785312 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.4617. Min Act: -0.1700
Data Index: 5560722 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7117. Min Range: -4.7117
Max Act: 4.4617. Min Act: -0.1700
Data Index: 6670326 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19