Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3646 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0404. Min Range: -4.0404
Max Act: 4.0404. Min Act: -0.1700
Data Index: 820686 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0404. Min Range: -4.0404
Max Act: 4.0091. Min Act: -0.1700
Data Index: 2542367 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9779. Min Act: -0.1700
Data Index: 1523517 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9779. Min Act: -0.1700
Data Index: 3601707 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9779. Min Act: -0.1700
Data Index: 109610 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9779. Min Act: -0.1700
Data Index: 8305090 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9466. Min Act: -0.1700
Data Index: 1260193 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9466. Min Act: -0.1700
Data Index: 4793144 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9154. Min Act: -0.1700
Data Index: 4127899 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9154. Min Act: -0.1700
Data Index: 5026728 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9154. Min Act: -0.1700
Data Index: 4574091 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9154. Min Act: -0.1700
Data Index: 5146829 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9154. Min Act: -0.1699
Data Index: 1933742 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9154. Min Act: -0.1700
Data Index: 6739536 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9154. Min Act: -0.1700
Data Index: 5567554 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9466. Min Act: -0.1700
Data Index: 5395563 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.9154. Min Act: -0.1700
Data Index: 427079 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.8841. Min Act: -0.1700
Data Index: 2343457 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.8841. Min Act: -0.1700
Data Index: 1257161 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0404. Min Range: -4.0404
Max Act: 3.8841. Min Act: -0.1700
Data Index: 388425 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19