Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3846 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1326. Min Range: -1.1326

Max Act: 1.1326. Min Act: -0.0000

Data Index: 707279 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 1.1326. Min Range: -1.1326

Max Act: 1.0361. Min Act: -0.0000

Data Index: 1036422 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.9385. Min Act: -0.0000

Data Index: 1174726 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.9752. Min Act: -0.0000

Data Index: 113922 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8116. Min Act: -0.0000

Data Index: 1196548 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8594. Min Act: -0.0000

Data Index: 975733 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8716. Min Act: -0.0000

Data Index: 369789 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1237725 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8646. Min Act: -0.0000

Data Index: 970752 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8935. Min Act: -0.0000

Data Index: 991973 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1188952 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8139. Min Act: -0.0000

Data Index: 1224992 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8767. Min Act: -0.0000

Data Index: 220552 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8415. Min Act: -0.0000

Data Index: 1229902 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8597. Min Act: -0.0000

Data Index: 1239805 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8277. Min Act: -0.0000

Data Index: 847889 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.7981. Min Act: -0.0000

Data Index: 66904 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.7917. Min Act: -0.0000

Data Index: 1066879 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8481. Min Act: -0.0000

Data Index: 318630 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 1.1326. Min Range: -1.1326

Max Act: 0.8727. Min Act: -0.0000

Data Index: 1133993 (C4 (Web Text))

Max Activating Token Index: 853