Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1839 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4558. Min Range: -4.4558
Max Act: 4.4558. Min Act: -0.1700
Data Index: 7942591 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4558. Min Range: -4.4558
Max Act: 4.4558. Min Act: -0.1700
Data Index: 365437 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4558. Min Range: -4.4558
Max Act: 4.4558. Min Act: -0.1700
Data Index: 5385907 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4558. Min Range: -4.4558
Max Act: 4.3621. Min Act: -0.1700
Data Index: 4992702 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4558. Min Range: -4.4558
Max Act: 4.3308. Min Act: -0.1700
Data Index: 26175 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4558. Min Range: -4.4558
Max Act: 4.2683. Min Act: -0.1700
Data Index: 2952843 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4558. Min Range: -4.4558
Max Act: 4.2683. Min Act: -0.1700
Data Index: 2894225 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4558. Min Range: -4.4558
Max Act: 4.2371. Min Act: -0.1700
Data Index: 4539453 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4558. Min Range: -4.4558
Max Act: 4.2371. Min Act: -0.1700
Data Index: 8319422 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4558. Min Range: -4.4558
Max Act: 4.2683. Min Act: -0.1700
Data Index: 7338708 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4558. Min Range: -4.4558
Max Act: 4.2058. Min Act: -0.1700
Data Index: 2174893 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4558. Min Range: -4.4558
Max Act: 4.1433. Min Act: -0.1700
Data Index: 2422353 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4558. Min Range: -4.4558
Max Act: 4.1433. Min Act: -0.1700
Data Index: 8112715 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4558. Min Range: -4.4558
Max Act: 4.1433. Min Act: -0.1700
Data Index: 5494690 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4558. Min Range: -4.4558
Max Act: 4.1433. Min Act: -0.1700
Data Index: 3572085 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4558. Min Range: -4.4558
Max Act: 4.1120. Min Act: -0.1700
Data Index: 7148055 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4558. Min Range: -4.4558
Max Act: 4.1433. Min Act: -0.1700
Data Index: 5184992 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4558. Min Range: -4.4558
Max Act: 4.1120. Min Act: -0.1700
Data Index: 2785603 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4558. Min Range: -4.4558
Max Act: 4.1120. Min Act: -0.1700
Data Index: 6552681 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4558. Min Range: -4.4558
Max Act: 4.1120. Min Act: -0.1700
Data Index: 2039158 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19