Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2052 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9491. Min Range: -6.9491
Max Act: 6.9491. Min Act: -0.1700
Data Index: 669342 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9491. Min Range: -6.9491
Max Act: 6.9491. Min Act: -0.1700
Data Index: 549728 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9491. Min Range: -6.9491
Max Act: 6.8554. Min Act: -0.1700
Data Index: 6397045 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9491. Min Range: -6.9491
Max Act: 6.8554. Min Act: -0.1700
Data Index: 788100 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9491. Min Range: -6.9491
Max Act: 6.8554. Min Act: -0.1700
Data Index: 5827570 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9491. Min Range: -6.9491
Max Act: 6.7929. Min Act: -0.1700
Data Index: 379170 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9491. Min Range: -6.9491
Max Act: 6.7929. Min Act: -0.1700
Data Index: 6715281 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9491. Min Range: -6.9491
Max Act: 6.7929. Min Act: -0.1700
Data Index: 6814770 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9491. Min Range: -6.9491
Max Act: 6.7304. Min Act: -0.1700
Data Index: 6003012 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9491. Min Range: -6.9491
Max Act: 6.7616. Min Act: -0.1700
Data Index: 5490592 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9491. Min Range: -6.9491
Max Act: 6.7304. Min Act: -0.1700
Data Index: 1001859 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9491. Min Range: -6.9491
Max Act: 6.7304. Min Act: -0.1700
Data Index: 5954260 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9491. Min Range: -6.9491
Max Act: 6.7304. Min Act: -0.1700
Data Index: 6300474 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9491. Min Range: -6.9491
Max Act: 6.7304. Min Act: -0.1700
Data Index: 1246517 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9491. Min Range: -6.9491
Max Act: 6.7304. Min Act: -0.1700
Data Index: 7268336 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9491. Min Range: -6.9491
Max Act: 6.6991. Min Act: -0.1700
Data Index: 1996810 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9491. Min Range: -6.9491
Max Act: 6.6991. Min Act: -0.1700
Data Index: 4952005 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9491. Min Range: -6.9491
Max Act: 6.6679. Min Act: -0.1700
Data Index: 3165686 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9491. Min Range: -6.9491
Max Act: 6.6679. Min Act: -0.1700
Data Index: 6141810 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9491. Min Range: -6.9491
Max Act: 6.6679. Min Act: -0.1693
Data Index: 4596488 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19