Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3174 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 21.6527. Min Range: -21.6527
Max Act: 21.6527. Min Act: -0.1700
Data Index: 6959508 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 21.6527. Min Range: -21.6527
Max Act: 21.1527. Min Act: -0.1700
Data Index: 4934758 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 21.6527. Min Range: -21.6527
Max Act: 21.0277. Min Act: -0.1700
Data Index: 1129234 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 21.6527. Min Range: -21.6527
Max Act: 21.0277. Min Act: -0.1699
Data Index: 2104194 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 21.6527. Min Range: -21.6527
Max Act: 20.9027. Min Act: -0.1700
Data Index: 2552734 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 21.6527. Min Range: -21.6527
Max Act: 20.7777. Min Act: -0.1700
Data Index: 2552732 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 21.6527. Min Range: -21.6527
Max Act: 20.5277. Min Act: -0.1700
Data Index: 1826984 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 21.6527. Min Range: -21.6527
Max Act: 20.4027. Min Act: -0.1700
Data Index: 2552735 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 21.6527. Min Range: -21.6527
Max Act: 20.5277. Min Act: -0.1700
Data Index: 2552738 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 21.6527. Min Range: -21.6527
Max Act: 20.4027. Min Act: -0.1700
Data Index: 4686189 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 21.6527. Min Range: -21.6527
Max Act: 20.2777. Min Act: -0.1700
Data Index: 3461127 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 21.6527. Min Range: -21.6527
Max Act: 20.1527. Min Act: -0.1700
Data Index: 2552733 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 21.6527. Min Range: -21.6527
Max Act: 20.1527. Min Act: -0.1700
Data Index: 5331326 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 21.6527. Min Range: -21.6527
Max Act: 20.0277. Min Act: -0.1700
Data Index: 3723662 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 21.6527. Min Range: -21.6527
Max Act: 20.0277. Min Act: -0.1700
Data Index: 3668235 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 21.6527. Min Range: -21.6527
Max Act: 20.0277. Min Act: -0.1700
Data Index: 4173929 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 21.6527. Min Range: -21.6527
Max Act: 19.9027. Min Act: -0.1700
Data Index: 7812872 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 21.6527. Min Range: -21.6527
Max Act: 19.9027. Min Act: -0.1700
Data Index: 1569510 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 21.6527. Min Range: -21.6527
Max Act: 19.9027. Min Act: -0.1700
Data Index: 1980928 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 21.6527. Min Range: -21.6527
Max Act: 19.9027. Min Act: -0.1700
Data Index: 6027282 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #19