Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3067 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0009. Min Range: -7.0009
Max Act: 7.0009. Min Act: -0.1700
Data Index: 8523021 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.9696. Min Act: -0.1700
Data Index: 7183514 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.8759. Min Act: -0.1700
Data Index: 8029312 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.8759. Min Act: -0.1700
Data Index: 1733830 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.9071. Min Act: -0.1700
Data Index: 3928080 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.8446. Min Act: -0.1700
Data Index: 277992 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.8134. Min Act: -0.1700
Data Index: 278000 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.8134. Min Act: -0.1700
Data Index: 2727552 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.7821. Min Act: -0.1700
Data Index: 665496 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.7509. Min Act: -0.1700
Data Index: 8026289 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.7509. Min Act: -0.1700
Data Index: 6186829 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.7196. Min Act: -0.1700
Data Index: 7331705 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.7196. Min Act: -0.1700
Data Index: 2956726 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.6884. Min Act: -0.1700
Data Index: 6953947 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.7196. Min Act: -0.1700
Data Index: 8153413 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.6884. Min Act: -0.1700
Data Index: 1605505 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.6571. Min Act: -0.1700
Data Index: 1806408 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.6259. Min Act: -0.1700
Data Index: 5239561 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.6259. Min Act: -0.1700
Data Index: 4988492 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0009. Min Range: -7.0009
Max Act: 6.6259. Min Act: -0.1700
Data Index: 5859912 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19