Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3344 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0298. Min Range: -4.0298
Max Act: 4.0298. Min Act: -0.1700
Data Index: 7653599 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0298. Min Range: -4.0298
Max Act: 3.9985. Min Act: -0.1700
Data Index: 8186396 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0298. Min Range: -4.0298
Max Act: 3.9985. Min Act: -0.1700
Data Index: 3952376 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0298. Min Range: -4.0298
Max Act: 3.9985. Min Act: -0.1700
Data Index: 7483508 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0298. Min Range: -4.0298
Max Act: 3.9673. Min Act: -0.1700
Data Index: 8548042 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0298. Min Range: -4.0298
Max Act: 3.9673. Min Act: -0.1700
Data Index: 8313462 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0298. Min Range: -4.0298
Max Act: 3.9360. Min Act: -0.1700
Data Index: 1905104 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0298. Min Range: -4.0298
Max Act: 3.9047. Min Act: -0.1700
Data Index: 6399156 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0298. Min Range: -4.0298
Max Act: 3.9047. Min Act: -0.1700
Data Index: 5617733 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0298. Min Range: -4.0298
Max Act: 3.9047. Min Act: -0.1700
Data Index: 4778038 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0298. Min Range: -4.0298
Max Act: 3.8735. Min Act: -0.1700
Data Index: 1674937 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0298. Min Range: -4.0298
Max Act: 3.8735. Min Act: -0.1700
Data Index: 807073 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0298. Min Range: -4.0298
Max Act: 3.8735. Min Act: -0.1700
Data Index: 3869367 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0298. Min Range: -4.0298
Max Act: 3.8735. Min Act: -0.1700
Data Index: 7281876 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0298. Min Range: -4.0298
Max Act: 3.8735. Min Act: -0.1700
Data Index: 704721 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0298. Min Range: -4.0298
Max Act: 3.8422. Min Act: -0.1700
Data Index: 7485037 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0298. Min Range: -4.0298
Max Act: 3.8735. Min Act: -0.1700
Data Index: 421865 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0298. Min Range: -4.0298
Max Act: 3.8735. Min Act: -0.1700
Data Index: 5323973 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0298. Min Range: -4.0298
Max Act: 3.8735. Min Act: -0.1700
Data Index: 1190326 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0298. Min Range: -4.0298
Max Act: 3.8735. Min Act: -0.1700
Data Index: 8537287 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19