Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1660 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.6306. Min Act: -0.1700
Data Index: 7049555 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.5681. Min Act: -0.1700
Data Index: 4609262 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.5681. Min Act: -0.1700
Data Index: 7642176 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.5681. Min Act: -0.1700
Data Index: 156924 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.5681. Min Act: -0.1698
Data Index: 4273715 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.5681. Min Act: -0.1700
Data Index: 3808548 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.5056. Min Act: -0.1700
Data Index: 3336578 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.5056. Min Act: -0.1700
Data Index: 3539672 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.5056. Min Act: -0.1700
Data Index: 3731386 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.5056. Min Act: -0.1700
Data Index: 6566861 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.5056. Min Act: -0.1700
Data Index: 3128222 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.5056. Min Act: -0.1700
Data Index: 6664602 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.5056. Min Act: -0.1700
Data Index: 573505 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.5056. Min Act: -0.1700
Data Index: 5908720 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.5056. Min Act: -0.1700
Data Index: 437029 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.4744. Min Act: -0.1700
Data Index: 6937883 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.4431. Min Act: -0.1700
Data Index: 590675 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.4744. Min Act: -0.1700
Data Index: 901793 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.4744. Min Act: -0.1700
Data Index: 4792000 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6306. Min Range: -6.6306
Max Act: 6.4744. Min Act: -0.1700
Data Index: 1425507 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19