Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3960 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3102. Min Range: -5.3102
Max Act: 5.3102. Min Act: -0.1700
Data Index: 8246899 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3102. Min Range: -5.3102
Max Act: 5.2165. Min Act: -0.1700
Data Index: 1524424 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3102. Min Range: -5.3102
Max Act: 5.0915. Min Act: -0.1700
Data Index: 2660533 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3102. Min Range: -5.3102
Max Act: 5.0290. Min Act: -0.1700
Data Index: 649037 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3102. Min Range: -5.3102
Max Act: 5.0915. Min Act: -0.1700
Data Index: 7462477 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3102. Min Range: -5.3102
Max Act: 5.1227. Min Act: -0.1700
Data Index: 5195219 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3102. Min Range: -5.3102
Max Act: 5.0290. Min Act: -0.1700
Data Index: 571610 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3102. Min Range: -5.3102
Max Act: 4.9665. Min Act: -0.1700
Data Index: 2209851 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3102. Min Range: -5.3102
Max Act: 5.0290. Min Act: -0.1700
Data Index: 3752784 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3102. Min Range: -5.3102
Max Act: 4.9665. Min Act: -0.1700
Data Index: 5385309 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3102. Min Range: -5.3102
Max Act: 4.9352. Min Act: -0.1700
Data Index: 4437799 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3102. Min Range: -5.3102
Max Act: 4.9040. Min Act: -0.1700
Data Index: 8689025 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3102. Min Range: -5.3102
Max Act: 4.9040. Min Act: -0.1700
Data Index: 7448647 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3102. Min Range: -5.3102
Max Act: 4.9040. Min Act: -0.1700
Data Index: 708591 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3102. Min Range: -5.3102
Max Act: 4.9040. Min Act: -0.1700
Data Index: 8480507 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3102. Min Range: -5.3102
Max Act: 4.8727. Min Act: -0.1700
Data Index: 5654182 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3102. Min Range: -5.3102
Max Act: 4.8727. Min Act: -0.1700
Data Index: 7525318 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3102. Min Range: -5.3102
Max Act: 4.8415. Min Act: -0.1700
Data Index: 218925 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3102. Min Range: -5.3102
Max Act: 4.8727. Min Act: -0.1700
Data Index: 3853869 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3102. Min Range: -5.3102
Max Act: 4.8415. Min Act: -0.1700
Data Index: 533249 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19