Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1952 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6017. Min Range: -4.6017
Max Act: 4.6017. Min Act: -0.1700
Data Index: 4744378 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6017. Min Range: -4.6017
Max Act: 4.5705. Min Act: -0.1700
Data Index: 8175425 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6017. Min Range: -4.6017
Max Act: 4.4142. Min Act: -0.1700
Data Index: 3865474 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6017. Min Range: -4.6017
Max Act: 4.3204. Min Act: -0.1700
Data Index: 2917313 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6017. Min Range: -4.6017
Max Act: 4.3204. Min Act: -0.1700
Data Index: 8720588 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6017. Min Range: -4.6017
Max Act: 4.3204. Min Act: -0.1700
Data Index: 7972200 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6017. Min Range: -4.6017
Max Act: 4.3204. Min Act: -0.1700
Data Index: 5187704 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6017. Min Range: -4.6017
Max Act: 4.2892. Min Act: -0.1700
Data Index: 7054910 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6017. Min Range: -4.6017
Max Act: 4.2267. Min Act: -0.1700
Data Index: 5445524 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6017. Min Range: -4.6017
Max Act: 4.1954. Min Act: -0.1700
Data Index: 2487121 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6017. Min Range: -4.6017
Max Act: 4.1642. Min Act: -0.1700
Data Index: 1787066 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6017. Min Range: -4.6017
Max Act: 4.1017. Min Act: -0.1700
Data Index: 1716383 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6017. Min Range: -4.6017
Max Act: 4.1329. Min Act: -0.1700
Data Index: 1827605 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6017. Min Range: -4.6017
Max Act: 4.0391. Min Act: -0.1700
Data Index: 8116681 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6017. Min Range: -4.6017
Max Act: 4.1329. Min Act: -0.1700
Data Index: 3357643 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6017. Min Range: -4.6017
Max Act: 4.0704. Min Act: -0.1700
Data Index: 4423262 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6017. Min Range: -4.6017
Max Act: 4.0704. Min Act: -0.1700
Data Index: 1827604 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6017. Min Range: -4.6017
Max Act: 4.0704. Min Act: -0.1700
Data Index: 2220641 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6017. Min Range: -4.6017
Max Act: 4.0704. Min Act: -0.1700
Data Index: 1570864 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6017. Min Range: -4.6017
Max Act: 4.0079. Min Act: -0.1700
Data Index: 1868097 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19