Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3121 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.3466. Min Act: -0.1691
Data Index: 5547873 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.3466. Min Act: -0.1700
Data Index: 4159404 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.3779. Min Act: -0.1699
Data Index: 6845041 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.3466. Min Act: -0.1700
Data Index: 3343665 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.3154. Min Act: -0.1700
Data Index: 5039729 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.2841. Min Act: -0.1700
Data Index: 4442120 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.3154. Min Act: -0.1693
Data Index: 2368317 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.2841. Min Act: -0.1700
Data Index: 4281294 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.2841. Min Act: -0.1700
Data Index: 4822181 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.2841. Min Act: -0.1700
Data Index: 8200087 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.2841. Min Act: -0.1700
Data Index: 3920144 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.2841. Min Act: -0.1700
Data Index: 3772888 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.2841. Min Act: -0.1700
Data Index: 7459285 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.2841. Min Act: -0.1688
Data Index: 1249485 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.2529. Min Act: -0.1700
Data Index: 6597386 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.2841. Min Act: -0.1700
Data Index: 6504481 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.2529. Min Act: -0.1700
Data Index: 4813298 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.2529. Min Act: -0.1700
Data Index: 1601014 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.2529. Min Act: -0.1699
Data Index: 4237195 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3779. Min Range: -5.3779
Max Act: 5.2529. Min Act: -0.1695
Data Index: 5609980 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19