Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3041 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2691. Min Range: -9.2691
Max Act: 9.2691. Min Act: -0.1700
Data Index: 5061369 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2691. Min Range: -9.2691
Max Act: 8.8316. Min Act: -0.1700
Data Index: 7640819 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2691. Min Range: -9.2691
Max Act: 8.6441. Min Act: -0.1700
Data Index: 3212066 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2691. Min Range: -9.2691
Max Act: 8.6441. Min Act: -0.1700
Data Index: 3629097 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2691. Min Range: -9.2691
Max Act: 8.5816. Min Act: -0.1700
Data Index: 6858971 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2691. Min Range: -9.2691
Max Act: 8.5191. Min Act: -0.1700
Data Index: 896436 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2691. Min Range: -9.2691
Max Act: 8.4566. Min Act: -0.1700
Data Index: 2899858 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2691. Min Range: -9.2691
Max Act: 8.4566. Min Act: -0.1700
Data Index: 3187337 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2691. Min Range: -9.2691
Max Act: 8.4566. Min Act: -0.1700
Data Index: 3152389 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2691. Min Range: -9.2691
Max Act: 8.3941. Min Act: -0.1700
Data Index: 6526368 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2691. Min Range: -9.2691
Max Act: 8.3941. Min Act: -0.1700
Data Index: 6627547 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2691. Min Range: -9.2691
Max Act: 8.3941. Min Act: -0.1700
Data Index: 5677384 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2691. Min Range: -9.2691
Max Act: 8.3316. Min Act: -0.1700
Data Index: 8470698 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2691. Min Range: -9.2691
Max Act: 8.3941. Min Act: -0.1700
Data Index: 8469338 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2691. Min Range: -9.2691
Max Act: 8.3941. Min Act: -0.1700
Data Index: 7169282 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2691. Min Range: -9.2691
Max Act: 8.3941. Min Act: -0.1700
Data Index: 6521698 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2691. Min Range: -9.2691
Max Act: 8.3316. Min Act: -0.1700
Data Index: 2624807 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2691. Min Range: -9.2691
Max Act: 8.3316. Min Act: -0.1700
Data Index: 885871 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2691. Min Range: -9.2691
Max Act: 8.3316. Min Act: -0.1700
Data Index: 2009717 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2691. Min Range: -9.2691
Max Act: 8.2691. Min Act: -0.1700
Data Index: 345353 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19