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

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

Neuron 690 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1437251 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1524768 (Python Code)

Max Activating Token Index: 581

Text #2

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1466946 (Python Code)

Max Activating Token Index: 689

Text #3

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1480805 (Python Code)

Max Activating Token Index: 536

Text #4

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1467241 (Python Code)

Max Activating Token Index: 690

Text #5

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1637139 (Python Code)

Max Activating Token Index: 866

Text #6

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0231. Min Act: -0.0002

Data Index: 81300 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1593001 (Python Code)

Max Activating Token Index: 973

Text #8

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1628686 (Python Code)

Max Activating Token Index: 454

Text #9

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1491250 (Python Code)

Max Activating Token Index: 933

Text #10

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0206. Min Act: -0.0002

Data Index: 1441098 (Python Code)

Max Activating Token Index: 827

Text #11

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1557666 (Python Code)

Max Activating Token Index: 687

Text #12

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1448810 (Python Code)

Max Activating Token Index: 321

Text #13

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1456727 (Python Code)

Max Activating Token Index: 871

Text #14

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1463980 (Python Code)

Max Activating Token Index: 677

Text #15

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0187. Min Act: -0.0002

Data Index: 1633965 (Python Code)

Max Activating Token Index: 889

Text #16

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0212. Min Act: -0.0002

Data Index: 1223328 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0188. Min Act: -0.0002

Data Index: 755326 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1623112 (Python Code)

Max Activating Token Index: 783

Text #19

Max Range: 0.0442. Min Range: -0.0442

Max Act: 0.0181. Min Act: -0.0002

Data Index: 1609134 (Python Code)

Max Activating Token Index: 770