Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 24 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.6810. Min Act: -0.1700
Data Index: 2512497 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4931. Min Act: -0.1700
Data Index: 7918621 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.4305. Min Act: -0.1700
Data Index: 1665013 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3834. Min Act: -0.1700
Data Index: 2268717 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3991. Min Act: -0.1700
Data Index: 6879300 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3834. Min Act: -0.1700
Data Index: 764011 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3991. Min Act: -0.1700
Data Index: 8208971 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3677. Min Act: -0.1700
Data Index: 6275384 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3521. Min Act: -0.1700
Data Index: 1412682 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3207. Min Act: -0.1700
Data Index: 3528693 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3364. Min Act: -0.1700
Data Index: 4096239 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3050. Min Act: -0.1700
Data Index: 3100606 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3050. Min Act: -0.1700
Data Index: 6333764 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.3207. Min Act: -0.1700
Data Index: 8030623 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.2893. Min Act: -0.1700
Data Index: 1790731 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.2893. Min Act: -0.1700
Data Index: 3976057 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.2736. Min Act: -0.1700
Data Index: 1876581 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.2736. Min Act: -0.1700
Data Index: 5668530 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.2736. Min Act: -0.1700
Data Index: 1463387 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6810. Min Range: -3.6810
Max Act: 3.2736. Min Act: -0.1700
Data Index: 1700832 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19