Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3026 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9227. Min Range: -6.9227
Max Act: 6.9227. Min Act: -0.1700
Data Index: 3561666 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9227. Min Range: -6.9227
Max Act: 6.7977. Min Act: -0.1700
Data Index: 4857481 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9227. Min Range: -6.9227
Max Act: 6.6727. Min Act: -0.1700
Data Index: 2169805 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9227. Min Range: -6.9227
Max Act: 6.6727. Min Act: -0.1700
Data Index: 800432 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9227. Min Range: -6.9227
Max Act: 6.5789. Min Act: -0.1700
Data Index: 4183738 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9227. Min Range: -6.9227
Max Act: 6.5477. Min Act: -0.1700
Data Index: 5555394 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9227. Min Range: -6.9227
Max Act: 6.5164. Min Act: -0.1700
Data Index: 5686633 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9227. Min Range: -6.9227
Max Act: 6.4852. Min Act: -0.1700
Data Index: 3244372 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9227. Min Range: -6.9227
Max Act: 6.4852. Min Act: -0.1700
Data Index: 2148673 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9227. Min Range: -6.9227
Max Act: 6.4852. Min Act: -0.1700
Data Index: 6655899 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9227. Min Range: -6.9227
Max Act: 6.4539. Min Act: -0.1700
Data Index: 4793292 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9227. Min Range: -6.9227
Max Act: 6.4539. Min Act: -0.1700
Data Index: 4591399 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9227. Min Range: -6.9227
Max Act: 6.4539. Min Act: -0.1700
Data Index: 6422634 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9227. Min Range: -6.9227
Max Act: 6.4539. Min Act: -0.1700
Data Index: 6097874 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9227. Min Range: -6.9227
Max Act: 6.4227. Min Act: -0.1700
Data Index: 2169795 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9227. Min Range: -6.9227
Max Act: 6.3914. Min Act: -0.1700
Data Index: 1121132 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9227. Min Range: -6.9227
Max Act: 6.3914. Min Act: -0.1700
Data Index: 2169801 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9227. Min Range: -6.9227
Max Act: 6.3914. Min Act: -0.1700
Data Index: 6556694 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9227. Min Range: -6.9227
Max Act: 6.3914. Min Act: -0.1700
Data Index: 2169808 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9227. Min Range: -6.9227
Max Act: 6.3602. Min Act: -0.1700
Data Index: 48556 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19