Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1659 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1647. Min Range: -6.1647
Max Act: 6.1647. Min Act: -0.1700
Data Index: 1436497 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1647. Min Range: -6.1647
Max Act: 6.0085. Min Act: -0.1700
Data Index: 3846822 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1647. Min Range: -6.1647
Max Act: 6.0397. Min Act: -0.1700
Data Index: 4846998 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1647. Min Range: -6.1647
Max Act: 5.9772. Min Act: -0.1700
Data Index: 8471873 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1647. Min Range: -6.1647
Max Act: 5.9460. Min Act: -0.1700
Data Index: 7009209 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1647. Min Range: -6.1647
Max Act: 5.9460. Min Act: -0.1700
Data Index: 8703654 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1647. Min Range: -6.1647
Max Act: 5.8835. Min Act: -0.1700
Data Index: 3844177 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1647. Min Range: -6.1647
Max Act: 5.8835. Min Act: -0.1700
Data Index: 234437 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1647. Min Range: -6.1647
Max Act: 5.8835. Min Act: -0.1700
Data Index: 5512353 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1647. Min Range: -6.1647
Max Act: 5.8835. Min Act: -0.1700
Data Index: 1018808 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1647. Min Range: -6.1647
Max Act: 5.8835. Min Act: -0.1700
Data Index: 3538028 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1647. Min Range: -6.1647
Max Act: 5.8210. Min Act: -0.1700
Data Index: 7079475 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1647. Min Range: -6.1647
Max Act: 5.8522. Min Act: -0.1700
Data Index: 936488 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1647. Min Range: -6.1647
Max Act: 5.8522. Min Act: -0.1700
Data Index: 5844263 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1647. Min Range: -6.1647
Max Act: 5.8522. Min Act: -0.1700
Data Index: 5970034 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1647. Min Range: -6.1647
Max Act: 5.8210. Min Act: -0.1700
Data Index: 7787895 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1647. Min Range: -6.1647
Max Act: 5.8210. Min Act: -0.1700
Data Index: 7717983 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1647. Min Range: -6.1647
Max Act: 5.8210. Min Act: -0.1700
Data Index: 6792768 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1647. Min Range: -6.1647
Max Act: 5.7897. Min Act: -0.1700
Data Index: 966714 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1647. Min Range: -6.1647
Max Act: 5.7897. Min Act: -0.1700
Data Index: 6810038 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #19