Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2689 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1235. Min Range: -6.1235
Max Act: 6.1235. Min Act: -0.1700
Data Index: 3913443 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1235. Min Range: -6.1235
Max Act: 6.0923. Min Act: -0.1700
Data Index: 6582893 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1235. Min Range: -6.1235
Max Act: 5.9985. Min Act: -0.1700
Data Index: 6778732 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1235. Min Range: -6.1235
Max Act: 5.9360. Min Act: -0.1700
Data Index: 6081174 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1235. Min Range: -6.1235
Max Act: 5.9048. Min Act: -0.1700
Data Index: 4799063 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1235. Min Range: -6.1235
Max Act: 5.8735. Min Act: -0.1700
Data Index: 3664460 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1235. Min Range: -6.1235
Max Act: 5.8735. Min Act: -0.1700
Data Index: 601785 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1235. Min Range: -6.1235
Max Act: 5.9048. Min Act: -0.1700
Data Index: 6319207 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1235. Min Range: -6.1235
Max Act: 5.8735. Min Act: -0.1700
Data Index: 3089649 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1235. Min Range: -6.1235
Max Act: 5.8423. Min Act: -0.1700
Data Index: 4482634 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1235. Min Range: -6.1235
Max Act: 5.8423. Min Act: -0.1700
Data Index: 6316600 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1235. Min Range: -6.1235
Max Act: 5.8110. Min Act: -0.1700
Data Index: 7292469 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1235. Min Range: -6.1235
Max Act: 5.7798. Min Act: -0.1700
Data Index: 7278196 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1235. Min Range: -6.1235
Max Act: 5.7485. Min Act: -0.1700
Data Index: 948662 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1235. Min Range: -6.1235
Max Act: 5.7798. Min Act: -0.1700
Data Index: 8354864 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1235. Min Range: -6.1235
Max Act: 5.7798. Min Act: -0.1700
Data Index: 4237343 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1235. Min Range: -6.1235
Max Act: 5.7798. Min Act: -0.1700
Data Index: 5691496 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1235. Min Range: -6.1235
Max Act: 5.7173. Min Act: -0.1700
Data Index: 5726186 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1235. Min Range: -6.1235
Max Act: 5.7485. Min Act: -0.1700
Data Index: 4087804 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1235. Min Range: -6.1235
Max Act: 5.7173. Min Act: -0.1700
Data Index: 5319717 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19