Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5891 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1718. Min Range: -9.1718
Max Act: 9.1718. Min Act: -0.1700
Data Index: 518695 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1718. Min Range: -9.1718
Max Act: 8.8593. Min Act: -0.1700
Data Index: 7046181 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1718. Min Range: -9.1718
Max Act: 8.8593. Min Act: -0.1700
Data Index: 1885086 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1718. Min Range: -9.1718
Max Act: 8.8593. Min Act: -0.1700
Data Index: 5737797 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1718. Min Range: -9.1718
Max Act: 8.7343. Min Act: -0.1700
Data Index: 7567012 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1718. Min Range: -9.1718
Max Act: 8.7343. Min Act: -0.1700
Data Index: 4988198 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1718. Min Range: -9.1718
Max Act: 8.7343. Min Act: -0.1700
Data Index: 6270826 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1718. Min Range: -9.1718
Max Act: 8.6718. Min Act: -0.1700
Data Index: 5169692 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1718. Min Range: -9.1718
Max Act: 8.6718. Min Act: -0.1700
Data Index: 2585822 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1718. Min Range: -9.1718
Max Act: 8.6718. Min Act: -0.1700
Data Index: 7340275 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1718. Min Range: -9.1718
Max Act: 8.6093. Min Act: -0.1700
Data Index: 8343260 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1718. Min Range: -9.1718
Max Act: 8.5468. Min Act: -0.1700
Data Index: 8787771 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1718. Min Range: -9.1718
Max Act: 8.5468. Min Act: -0.1700
Data Index: 1526403 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1718. Min Range: -9.1718
Max Act: 8.4843. Min Act: -0.1700
Data Index: 8728405 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1718. Min Range: -9.1718
Max Act: 8.4843. Min Act: -0.1700
Data Index: 4122113 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1718. Min Range: -9.1718
Max Act: 8.4843. Min Act: -0.1700
Data Index: 4150927 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1718. Min Range: -9.1718
Max Act: 8.4843. Min Act: -0.1700
Data Index: 4429061 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1718. Min Range: -9.1718
Max Act: 8.4843. Min Act: -0.1700
Data Index: 8047032 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1718. Min Range: -9.1718
Max Act: 8.4218. Min Act: -0.1700
Data Index: 80044 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1718. Min Range: -9.1718
Max Act: 8.4218. Min Act: -0.1700
Data Index: 6623468 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19