Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0456. Min Range: -9.0456
Max Act: 9.0456. Min Act: -0.1700
Data Index: 1291709 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0456. Min Range: -9.0456
Max Act: 8.4206. Min Act: -0.1700
Data Index: 90841 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0456. Min Range: -9.0456
Max Act: 8.4206. Min Act: -0.1700
Data Index: 8577452 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0456. Min Range: -9.0456
Max Act: 8.4206. Min Act: -0.1700
Data Index: 5101860 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0456. Min Range: -9.0456
Max Act: 8.2956. Min Act: -0.1700
Data Index: 6699549 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0456. Min Range: -9.0456
Max Act: 8.2956. Min Act: -0.1700
Data Index: 3194897 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0456. Min Range: -9.0456
Max Act: 8.2331. Min Act: -0.1700
Data Index: 3860287 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0456. Min Range: -9.0456
Max Act: 8.2331. Min Act: -0.1700
Data Index: 4950619 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0456. Min Range: -9.0456
Max Act: 8.2331. Min Act: -0.1700
Data Index: 1068685 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0456. Min Range: -9.0456
Max Act: 8.1706. Min Act: -0.1700
Data Index: 1640274 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0456. Min Range: -9.0456
Max Act: 8.0769. Min Act: -0.1700
Data Index: 881829 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0456. Min Range: -9.0456
Max Act: 8.0144. Min Act: -0.1700
Data Index: 8319602 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0456. Min Range: -9.0456
Max Act: 8.0144. Min Act: -0.1700
Data Index: 3493439 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0456. Min Range: -9.0456
Max Act: 7.9831. Min Act: -0.1700
Data Index: 5272034 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0456. Min Range: -9.0456
Max Act: 7.9519. Min Act: -0.1700
Data Index: 2942098 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0456. Min Range: -9.0456
Max Act: 7.9519. Min Act: -0.1700
Data Index: 1503414 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0456. Min Range: -9.0456
Max Act: 7.9206. Min Act: -0.1700
Data Index: 6355373 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0456. Min Range: -9.0456
Max Act: 7.9519. Min Act: -0.1700
Data Index: 8134371 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0456. Min Range: -9.0456
Max Act: 7.9206. Min Act: -0.1700
Data Index: 1479602 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0456. Min Range: -9.0456
Max Act: 7.8894. Min Act: -0.1700
Data Index: 7034004 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19