Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5867 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.7016. Min Range: -12.7016
Max Act: 12.7016. Min Act: -0.1700
Data Index: 8468636 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.7016. Min Range: -12.7016
Max Act: 12.4516. Min Act: -0.1700
Data Index: 2156893 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.7016. Min Range: -12.7016
Max Act: 12.3891. Min Act: -0.1700
Data Index: 5046896 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.7016. Min Range: -12.7016
Max Act: 12.2641. Min Act: -0.1700
Data Index: 2394893 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.7016. Min Range: -12.7016
Max Act: 12.0766. Min Act: -0.1700
Data Index: 8340631 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.7016. Min Range: -12.7016
Max Act: 12.0766. Min Act: -0.1700
Data Index: 8287264 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.7016. Min Range: -12.7016
Max Act: 12.0141. Min Act: -0.1700
Data Index: 2683358 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.7016. Min Range: -12.7016
Max Act: 12.1391. Min Act: -0.1700
Data Index: 3389513 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.7016. Min Range: -12.7016
Max Act: 12.0141. Min Act: -0.1700
Data Index: 6724539 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.7016. Min Range: -12.7016
Max Act: 12.0141. Min Act: -0.1700
Data Index: 116173 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.7016. Min Range: -12.7016
Max Act: 12.0141. Min Act: -0.1700
Data Index: 4818078 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.7016. Min Range: -12.7016
Max Act: 11.9516. Min Act: -0.1700
Data Index: 7304527 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.7016. Min Range: -12.7016
Max Act: 11.9516. Min Act: -0.1700
Data Index: 5941068 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.7016. Min Range: -12.7016
Max Act: 12.0141. Min Act: -0.1700
Data Index: 6020652 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.7016. Min Range: -12.7016
Max Act: 12.0141. Min Act: -0.1700
Data Index: 6160211 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.7016. Min Range: -12.7016
Max Act: 11.8891. Min Act: -0.1700
Data Index: 8629585 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.7016. Min Range: -12.7016
Max Act: 11.8266. Min Act: -0.1700
Data Index: 8088111 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.7016. Min Range: -12.7016
Max Act: 11.7641. Min Act: -0.1700
Data Index: 7500105 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.7016. Min Range: -12.7016
Max Act: 11.8266. Min Act: -0.1700
Data Index: 6819768 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.7016. Min Range: -12.7016
Max Act: 11.6391. Min Act: -0.1700
Data Index: 7831662 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19