Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3490 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7004. Min Range: -4.7004
Max Act: 4.7004. Min Act: -0.1700
Data Index: 3268550 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7004. Min Range: -4.7004
Max Act: 4.6379. Min Act: -0.1700
Data Index: 3581729 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7004. Min Range: -4.7004
Max Act: 4.5441. Min Act: -0.1700
Data Index: 7655219 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7004. Min Range: -4.7004
Max Act: 4.5441. Min Act: -0.1700
Data Index: 8155432 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7004. Min Range: -4.7004
Max Act: 4.5754. Min Act: -0.1700
Data Index: 1683460 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7004. Min Range: -4.7004
Max Act: 4.5129. Min Act: -0.1700
Data Index: 1043413 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7004. Min Range: -4.7004
Max Act: 4.4816. Min Act: -0.1700
Data Index: 3332681 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7004. Min Range: -4.7004
Max Act: 4.4816. Min Act: -0.1700
Data Index: 1684921 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7004. Min Range: -4.7004
Max Act: 4.4816. Min Act: -0.1700
Data Index: 3628538 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7004. Min Range: -4.7004
Max Act: 4.5129. Min Act: -0.1700
Data Index: 3298676 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7004. Min Range: -4.7004
Max Act: 4.3879. Min Act: -0.1700
Data Index: 3004468 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7004. Min Range: -4.7004
Max Act: 4.4191. Min Act: -0.1700
Data Index: 7320981 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7004. Min Range: -4.7004
Max Act: 4.3879. Min Act: -0.1700
Data Index: 3678277 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7004. Min Range: -4.7004
Max Act: 4.3566. Min Act: -0.1700
Data Index: 725987 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7004. Min Range: -4.7004
Max Act: 4.3566. Min Act: -0.1700
Data Index: 5484526 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7004. Min Range: -4.7004
Max Act: 4.3254. Min Act: -0.1700
Data Index: 3537093 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7004. Min Range: -4.7004
Max Act: 4.3566. Min Act: -0.1700
Data Index: 6462227 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7004. Min Range: -4.7004
Max Act: 4.3254. Min Act: -0.1700
Data Index: 7408995 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7004. Min Range: -4.7004
Max Act: 4.3254. Min Act: -0.1700
Data Index: 1794150 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7004. Min Range: -4.7004
Max Act: 4.3566. Min Act: -0.1700
Data Index: 1889386 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19