Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1837 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1046. Min Range: -6.1046
Max Act: 6.1046. Min Act: -0.1700
Data Index: 1829734 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1046. Min Range: -6.1046
Max Act: 6.0734. Min Act: -0.1700
Data Index: 7076386 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1046. Min Range: -6.1046
Max Act: 6.0109. Min Act: -0.1700
Data Index: 4515646 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1046. Min Range: -6.1046
Max Act: 5.9171. Min Act: -0.1700
Data Index: 6608879 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1046. Min Range: -6.1046
Max Act: 5.8234. Min Act: -0.1700
Data Index: 7472007 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1046. Min Range: -6.1046
Max Act: 5.8546. Min Act: -0.1700
Data Index: 1426817 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1046. Min Range: -6.1046
Max Act: 5.7609. Min Act: -0.1700
Data Index: 8783041 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1046. Min Range: -6.1046
Max Act: 5.6984. Min Act: -0.1700
Data Index: 5434867 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1046. Min Range: -6.1046
Max Act: 5.6671. Min Act: -0.1700
Data Index: 6134714 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1046. Min Range: -6.1046
Max Act: 5.6671. Min Act: -0.1700
Data Index: 4137769 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1046. Min Range: -6.1046
Max Act: 5.6046. Min Act: -0.1700
Data Index: 7585223 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1046. Min Range: -6.1046
Max Act: 5.6046. Min Act: -0.1700
Data Index: 191949 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1046. Min Range: -6.1046
Max Act: 5.5734. Min Act: -0.1700
Data Index: 7854250 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1046. Min Range: -6.1046
Max Act: 5.5734. Min Act: -0.1700
Data Index: 326485 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1046. Min Range: -6.1046
Max Act: 5.5421. Min Act: -0.1700
Data Index: 4759552 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1046. Min Range: -6.1046
Max Act: 5.5421. Min Act: -0.1700
Data Index: 3022289 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1046. Min Range: -6.1046
Max Act: 5.5109. Min Act: -0.1700
Data Index: 6352591 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1046. Min Range: -6.1046
Max Act: 5.5109. Min Act: -0.1700
Data Index: 3897672 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1046. Min Range: -6.1046
Max Act: 5.5109. Min Act: -0.1700
Data Index: 1501664 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1046. Min Range: -6.1046
Max Act: 5.5109. Min Act: -0.1700
Data Index: 1132853 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #19