Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5827 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.8194. Min Act: -0.1700
Data Index: 3740307 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.7569. Min Act: -0.1700
Data Index: 8427261 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.7256. Min Act: -0.1700
Data Index: 8667686 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.7256. Min Act: -0.1700
Data Index: 1640815 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.7256. Min Act: -0.1700
Data Index: 4076753 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.7256. Min Act: -0.1700
Data Index: 5638272 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.6944. Min Act: -0.1700
Data Index: 3921483 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.6944. Min Act: -0.1700
Data Index: 2442004 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.6631. Min Act: -0.1700
Data Index: 6798223 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.6631. Min Act: -0.1700
Data Index: 362003 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.6319. Min Act: -0.1700
Data Index: 3290937 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.6319. Min Act: -0.1700
Data Index: 4973091 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.6319. Min Act: -0.1700
Data Index: 6528658 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.6319. Min Act: -0.1700
Data Index: 4004339 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.6319. Min Act: -0.1700
Data Index: 7043561 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.5694. Min Act: -0.1700
Data Index: 3653348 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.6006. Min Act: -0.1700
Data Index: 6578275 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.6006. Min Act: -0.1700
Data Index: 3111863 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.5694. Min Act: -0.1700
Data Index: 8613147 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8194. Min Range: -5.8194
Max Act: 5.5694. Min Act: -0.1700
Data Index: 1390992 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19