Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5202 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4985. Min Range: -4.4985
Max Act: 4.4985. Min Act: -0.1700
Data Index: 7370410 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4985. Min Range: -4.4985
Max Act: 4.0610. Min Act: -0.1700
Data Index: 3726379 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4985. Min Range: -4.4985
Max Act: 4.0297. Min Act: -0.1700
Data Index: 3871289 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4985. Min Range: -4.4985
Max Act: 3.9985. Min Act: -0.1700
Data Index: 6024729 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4985. Min Range: -4.4985
Max Act: 3.9672. Min Act: -0.1700
Data Index: 3576790 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4985. Min Range: -4.4985
Max Act: 3.9360. Min Act: -0.1700
Data Index: 1901144 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4985. Min Range: -4.4985
Max Act: 3.9360. Min Act: -0.1700
Data Index: 8216033 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4985. Min Range: -4.4985
Max Act: 3.8734. Min Act: -0.1700
Data Index: 6678204 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4985. Min Range: -4.4985
Max Act: 3.9047. Min Act: -0.1700
Data Index: 7136577 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4985. Min Range: -4.4985
Max Act: 3.8734. Min Act: -0.1700
Data Index: 5755932 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4985. Min Range: -4.4985
Max Act: 3.9047. Min Act: -0.1700
Data Index: 1582506 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4985. Min Range: -4.4985
Max Act: 3.8734. Min Act: -0.1700
Data Index: 783798 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4985. Min Range: -4.4985
Max Act: 3.8734. Min Act: -0.1700
Data Index: 1901142 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4985. Min Range: -4.4985
Max Act: 3.8734. Min Act: -0.1700
Data Index: 4028820 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4985. Min Range: -4.4985
Max Act: 3.8422. Min Act: -0.1700
Data Index: 2903787 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4985. Min Range: -4.4985
Max Act: 3.8734. Min Act: -0.1700
Data Index: 6552681 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4985. Min Range: -4.4985
Max Act: 3.8422. Min Act: -0.1700
Data Index: 961059 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4985. Min Range: -4.4985
Max Act: 3.8109. Min Act: -0.1700
Data Index: 4419852 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4985. Min Range: -4.4985
Max Act: 3.8422. Min Act: -0.1700
Data Index: 6124691 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4985. Min Range: -4.4985
Max Act: 3.7796. Min Act: -0.1700
Data Index: 5155580 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19