Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2724 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0745. Min Range: -5.0745
Max Act: 5.0745. Min Act: -0.1700
Data Index: 2228195 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0745. Min Range: -5.0745
Max Act: 4.9495. Min Act: -0.1700
Data Index: 543095 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0745. Min Range: -5.0745
Max Act: 4.8558. Min Act: -0.1700
Data Index: 967142 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0745. Min Range: -5.0745
Max Act: 4.8558. Min Act: -0.1700
Data Index: 5492743 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0745. Min Range: -5.0745
Max Act: 4.8245. Min Act: -0.1700
Data Index: 1391067 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0745. Min Range: -5.0745
Max Act: 4.8245. Min Act: -0.1700
Data Index: 1981239 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0745. Min Range: -5.0745
Max Act: 4.7620. Min Act: -0.1700
Data Index: 6656502 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0745. Min Range: -5.0745
Max Act: 4.7933. Min Act: -0.1700
Data Index: 5484767 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0745. Min Range: -5.0745
Max Act: 4.7620. Min Act: -0.1700
Data Index: 1060504 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0745. Min Range: -5.0745
Max Act: 4.7308. Min Act: -0.1700
Data Index: 1947555 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0745. Min Range: -5.0745
Max Act: 4.7308. Min Act: -0.1700
Data Index: 8340594 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0745. Min Range: -5.0745
Max Act: 4.7308. Min Act: -0.1700
Data Index: 6066537 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0745. Min Range: -5.0745
Max Act: 4.7308. Min Act: -0.1700
Data Index: 1914334 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0745. Min Range: -5.0745
Max Act: 4.6683. Min Act: -0.1700
Data Index: 4337690 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0745. Min Range: -5.0745
Max Act: 4.6995. Min Act: -0.1700
Data Index: 643223 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0745. Min Range: -5.0745
Max Act: 4.6995. Min Act: -0.1700
Data Index: 8452048 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0745. Min Range: -5.0745
Max Act: 4.6995. Min Act: -0.1700
Data Index: 458328 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0745. Min Range: -5.0745
Max Act: 4.6683. Min Act: -0.1700
Data Index: 1811282 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0745. Min Range: -5.0745
Max Act: 4.6683. Min Act: -0.1700
Data Index: 5463475 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0745. Min Range: -5.0745
Max Act: 4.6370. Min Act: -0.1700
Data Index: 3750604 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19