Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3903 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1398. Min Act: -0.0002

Data Index: 1496553 (Python Code)

Max Activating Token Index: 636

Text #1

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1255. Min Act: -0.0002

Data Index: 1586646 (Python Code)

Max Activating Token Index: 83

Text #2

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1211. Min Act: -0.0002

Data Index: 1377880 (Python Code)

Max Activating Token Index: 935

Text #3

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1170. Min Act: -0.0002

Data Index: 1475276 (Python Code)

Max Activating Token Index: 389

Text #4

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1227. Min Act: -0.0002

Data Index: 1388419 (Python Code)

Max Activating Token Index: 458

Text #5

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1181. Min Act: -0.0002

Data Index: 1547351 (Python Code)

Max Activating Token Index: 970

Text #6

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1181. Min Act: -0.0002

Data Index: 1618252 (Python Code)

Max Activating Token Index: 144

Text #7

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1211. Min Act: -0.0002

Data Index: 1623176 (Python Code)

Max Activating Token Index: 210

Text #8

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1231. Min Act: -0.0002

Data Index: 1564977 (Python Code)

Max Activating Token Index: 734

Text #9

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1159. Min Act: -0.0002

Data Index: 1455706 (Python Code)

Max Activating Token Index: 564

Text #10

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1069. Min Act: -0.0002

Data Index: 1635676 (Python Code)

Max Activating Token Index: 1000

Text #11

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1190. Min Act: -0.0002

Data Index: 1524441 (Python Code)

Max Activating Token Index: 629

Text #12

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1158. Min Act: -0.0002

Data Index: 1527139 (Python Code)

Max Activating Token Index: 773

Text #13

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1044. Min Act: -0.0002

Data Index: 1526991 (Python Code)

Max Activating Token Index: 258

Text #14

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1116. Min Act: -0.0002

Data Index: 1635699 (Python Code)

Max Activating Token Index: 517

Text #15

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1115. Min Act: -0.0002

Data Index: 1418140 (Python Code)

Max Activating Token Index: 478

Text #16

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1058. Min Act: -0.0002

Data Index: 1552349 (Python Code)

Max Activating Token Index: 254

Text #17

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1068. Min Act: -0.0002

Data Index: 1442810 (Python Code)

Max Activating Token Index: 906

Text #18

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1131. Min Act: -0.0002

Data Index: 1456992 (Python Code)

Max Activating Token Index: 54

Text #19

Max Range: 0.1398. Min Range: -0.1398

Max Act: 0.1049. Min Act: -0.0002

Data Index: 1428309 (Python Code)

Max Activating Token Index: 122