Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2061 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9996. Min Range: -4.9996
Max Act: 4.9996. Min Act: -0.1700
Data Index: 7220942 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9996. Min Range: -4.9996
Max Act: 4.9996. Min Act: -0.1700
Data Index: 2408654 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9996. Min Range: -4.9996
Max Act: 4.9684. Min Act: -0.1700
Data Index: 8551870 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9996. Min Range: -4.9996
Max Act: 4.9371. Min Act: -0.1700
Data Index: 1322908 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9996. Min Range: -4.9996
Max Act: 4.9371. Min Act: -0.1699
Data Index: 4831987 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9996. Min Range: -4.9996
Max Act: 4.9371. Min Act: -0.1700
Data Index: 4745834 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9996. Min Range: -4.9996
Max Act: 4.9371. Min Act: -0.1700
Data Index: 4732601 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9996. Min Range: -4.9996
Max Act: 4.9371. Min Act: -0.1700
Data Index: 4500640 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9996. Min Range: -4.9996
Max Act: 4.9371. Min Act: -0.1700
Data Index: 4891329 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9996. Min Range: -4.9996
Max Act: 4.9371. Min Act: -0.1700
Data Index: 494117 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9996. Min Range: -4.9996
Max Act: 4.9371. Min Act: -0.1700
Data Index: 4477512 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9996. Min Range: -4.9996
Max Act: 4.9059. Min Act: -0.1700
Data Index: 6975232 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9996. Min Range: -4.9996
Max Act: 4.9059. Min Act: -0.1700
Data Index: 5663722 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9996. Min Range: -4.9996
Max Act: 4.8746. Min Act: -0.1700
Data Index: 7442855 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9996. Min Range: -4.9996
Max Act: 4.8434. Min Act: -0.1700
Data Index: 3218308 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9996. Min Range: -4.9996
Max Act: 4.8121. Min Act: -0.1700
Data Index: 5579871 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9996. Min Range: -4.9996
Max Act: 4.8121. Min Act: -0.1700
Data Index: 986463 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9996. Min Range: -4.9996
Max Act: 4.8121. Min Act: -0.1700
Data Index: 7933078 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9996. Min Range: -4.9996
Max Act: 4.8121. Min Act: -0.1700
Data Index: 3484967 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9996. Min Range: -4.9996
Max Act: 4.7809. Min Act: -0.1700
Data Index: 5391251 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19