Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3000 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2015. Min Range: -8.2015
Max Act: 8.2015. Min Act: -0.1700
Data Index: 7534799 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2015. Min Range: -8.2015
Max Act: 8.1703. Min Act: -0.1700
Data Index: 1290802 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2015. Min Range: -8.2015
Max Act: 7.8266. Min Act: -0.1700
Data Index: 1290801 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2015. Min Range: -8.2015
Max Act: 7.6078. Min Act: -0.1700
Data Index: 3394066 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2015. Min Range: -8.2015
Max Act: 7.6078. Min Act: -0.1700
Data Index: 2762084 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2015. Min Range: -8.2015
Max Act: 7.5453. Min Act: -0.1700
Data Index: 3141951 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2015. Min Range: -8.2015
Max Act: 7.5141. Min Act: -0.1700
Data Index: 8708584 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2015. Min Range: -8.2015
Max Act: 7.4516. Min Act: -0.1700
Data Index: 6994646 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2015. Min Range: -8.2015
Max Act: 7.4203. Min Act: -0.1700
Data Index: 4068854 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2015. Min Range: -8.2015
Max Act: 7.3266. Min Act: -0.1700
Data Index: 2025836 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2015. Min Range: -8.2015
Max Act: 7.3266. Min Act: -0.1700
Data Index: 5043021 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2015. Min Range: -8.2015
Max Act: 7.2641. Min Act: -0.1700
Data Index: 4889933 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2015. Min Range: -8.2015
Max Act: 7.2328. Min Act: -0.1700
Data Index: 1935806 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2015. Min Range: -8.2015
Max Act: 7.2328. Min Act: -0.1700
Data Index: 1193746 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2015. Min Range: -8.2015
Max Act: 7.1703. Min Act: -0.1700
Data Index: 5202397 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2015. Min Range: -8.2015
Max Act: 7.2016. Min Act: -0.1700
Data Index: 6668576 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2015. Min Range: -8.2015
Max Act: 7.1703. Min Act: -0.1700
Data Index: 6211739 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2015. Min Range: -8.2015
Max Act: 7.2328. Min Act: -0.1700
Data Index: 627805 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2015. Min Range: -8.2015
Max Act: 7.1703. Min Act: -0.1700
Data Index: 1496278 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2015. Min Range: -8.2015
Max Act: 7.1703. Min Act: -0.1700
Data Index: 3739931 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19