Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2737 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9733. Min Range: -2.9733
Max Act: 2.9733. Min Act: -0.1700
Data Index: 8626761 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9733. Min Range: -2.9733
Max Act: 2.9416. Min Act: -0.1700
Data Index: 6316479 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9733. Min Range: -2.9733
Max Act: 2.9258. Min Act: -0.1700
Data Index: 7765416 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9733. Min Range: -2.9733
Max Act: 2.9258. Min Act: -0.1700
Data Index: 5916830 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9733. Min Range: -2.9733
Max Act: 2.9258. Min Act: -0.1700
Data Index: 863326 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9733. Min Range: -2.9733
Max Act: 2.8623. Min Act: -0.1700
Data Index: 6124755 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9733. Min Range: -2.9733
Max Act: 2.8623. Min Act: -0.1700
Data Index: 4936390 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9733. Min Range: -2.9733
Max Act: 2.8465. Min Act: -0.1700
Data Index: 5916829 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9733. Min Range: -2.9733
Max Act: 2.8465. Min Act: -0.1700
Data Index: 1785399 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9733. Min Range: -2.9733
Max Act: 2.7987. Min Act: -0.1700
Data Index: 2039064 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9733. Min Range: -2.9733
Max Act: 2.7509. Min Act: -0.1700
Data Index: 459038 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9733. Min Range: -2.9733
Max Act: 2.7509. Min Act: -0.1700
Data Index: 7965441 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9733. Min Range: -2.9733
Max Act: 2.7669. Min Act: -0.1700
Data Index: 5417778 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9733. Min Range: -2.9733
Max Act: 2.7669. Min Act: -0.1700
Data Index: 5141946 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9733. Min Range: -2.9733
Max Act: 2.7669. Min Act: -0.1700
Data Index: 8715604 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9733. Min Range: -2.9733
Max Act: 2.7509. Min Act: -0.1700
Data Index: 5242339 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9733. Min Range: -2.9733
Max Act: 2.7190. Min Act: -0.1700
Data Index: 3633282 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9733. Min Range: -2.9733
Max Act: 2.7349. Min Act: -0.1700
Data Index: 1877937 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9733. Min Range: -2.9733
Max Act: 2.7349. Min Act: -0.1700
Data Index: 425748 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9733. Min Range: -2.9733
Max Act: 2.7190. Min Act: -0.1700
Data Index: 3973918 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19