Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5878 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1556. Min Range: -3.1556
Max Act: 3.1556. Min Act: -0.1700
Data Index: 4415899 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1556. Min Range: -3.1556
Max Act: 3.1556. Min Act: -0.1700
Data Index: 5071971 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1556. Min Range: -3.1556
Max Act: 3.1083. Min Act: -0.1700
Data Index: 6778472 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1556. Min Range: -3.1556
Max Act: 3.0926. Min Act: -0.1700
Data Index: 274368 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1556. Min Range: -3.1556
Max Act: 3.0768. Min Act: -0.1700
Data Index: 165493 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1556. Min Range: -3.1556
Max Act: 3.0768. Min Act: -0.1700
Data Index: 6535860 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1556. Min Range: -3.1556
Max Act: 3.0768. Min Act: -0.1700
Data Index: 1813194 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1556. Min Range: -3.1556
Max Act: 3.0610. Min Act: -0.1700
Data Index: 6953494 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1556. Min Range: -3.1556
Max Act: 3.0610. Min Act: -0.1700
Data Index: 5322833 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1556. Min Range: -3.1556
Max Act: 3.0453. Min Act: -0.1700
Data Index: 7715206 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1556. Min Range: -3.1556
Max Act: 3.0453. Min Act: -0.1700
Data Index: 1550741 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1556. Min Range: -3.1556
Max Act: 3.0295. Min Act: -0.1700
Data Index: 8649538 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1556. Min Range: -3.1556
Max Act: 3.0295. Min Act: -0.1700
Data Index: 594582 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1556. Min Range: -3.1556
Max Act: 3.0295. Min Act: -0.1700
Data Index: 1185361 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1556. Min Range: -3.1556
Max Act: 2.9979. Min Act: -0.1700
Data Index: 6413784 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1556. Min Range: -3.1556
Max Act: 3.0295. Min Act: -0.1700
Data Index: 7602015 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1556. Min Range: -3.1556
Max Act: 2.9979. Min Act: -0.1700
Data Index: 7207645 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1556. Min Range: -3.1556
Max Act: 2.9979. Min Act: -0.1700
Data Index: 2409443 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1556. Min Range: -3.1556
Max Act: 2.9979. Min Act: -0.1700
Data Index: 6393481 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1556. Min Range: -3.1556
Max Act: 2.9979. Min Act: -0.1700
Data Index: 6417161 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19