Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1307 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8556. Min Range: -6.8556
Max Act: 6.8556. Min Act: -0.1700
Data Index: 1716894 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8556. Min Range: -6.8556
Max Act: 6.3244. Min Act: -0.1700
Data Index: 3518482 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8556. Min Range: -6.8556
Max Act: 6.2931. Min Act: -0.1700
Data Index: 7761583 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8556. Min Range: -6.8556
Max Act: 6.2619. Min Act: -0.1700
Data Index: 6615003 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8556. Min Range: -6.8556
Max Act: 6.1056. Min Act: -0.1700
Data Index: 4372831 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8556. Min Range: -6.8556
Max Act: 6.1056. Min Act: -0.1700
Data Index: 4305235 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8556. Min Range: -6.8556
Max Act: 6.0744. Min Act: -0.1700
Data Index: 3518483 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8556. Min Range: -6.8556
Max Act: 6.0119. Min Act: -0.1700
Data Index: 7366803 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8556. Min Range: -6.8556
Max Act: 6.0431. Min Act: -0.1700
Data Index: 3729256 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8556. Min Range: -6.8556
Max Act: 6.0744. Min Act: -0.1700
Data Index: 2362529 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8556. Min Range: -6.8556
Max Act: 6.0119. Min Act: -0.1700
Data Index: 4828844 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8556. Min Range: -6.8556
Max Act: 6.0119. Min Act: -0.1700
Data Index: 6130919 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8556. Min Range: -6.8556
Max Act: 6.0119. Min Act: -0.1700
Data Index: 727104 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8556. Min Range: -6.8556
Max Act: 5.9806. Min Act: -0.1700
Data Index: 8000854 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8556. Min Range: -6.8556
Max Act: 5.9806. Min Act: -0.1700
Data Index: 1469380 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8556. Min Range: -6.8556
Max Act: 5.9806. Min Act: -0.1700
Data Index: 4014657 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8556. Min Range: -6.8556
Max Act: 5.9806. Min Act: -0.1700
Data Index: 2839106 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8556. Min Range: -6.8556
Max Act: 5.9806. Min Act: -0.1700
Data Index: 2189304 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8556. Min Range: -6.8556
Max Act: 5.9806. Min Act: -0.1700
Data Index: 6483913 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8556. Min Range: -6.8556
Max Act: 5.9494. Min Act: -0.1700
Data Index: 7091082 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19