Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2011 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1251. Min Act: -0.0002

Data Index: 1502362 (Python Code)

Max Activating Token Index: 817

Text #1

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1243. Min Act: -0.0002

Data Index: 1582509 (Python Code)

Max Activating Token Index: 26

Text #2

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1234. Min Act: -0.0002

Data Index: 1593387 (Python Code)

Max Activating Token Index: 20

Text #3

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1227. Min Act: -0.0002

Data Index: 1633737 (Python Code)

Max Activating Token Index: 733

Text #4

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1204. Min Act: -0.0002

Data Index: 1409891 (Python Code)

Max Activating Token Index: 223

Text #5

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1263. Min Act: -0.0002

Data Index: 1387542 (Python Code)

Max Activating Token Index: 457

Text #6

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1207. Min Act: -0.0002

Data Index: 1545285 (Python Code)

Max Activating Token Index: 686

Text #7

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1158. Min Act: -0.0002

Data Index: 1485447 (Python Code)

Max Activating Token Index: 877

Text #8

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1153. Min Act: -0.0002

Data Index: 1447533 (Python Code)

Max Activating Token Index: 557

Text #9

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1176. Min Act: -0.0002

Data Index: 1618797 (Python Code)

Max Activating Token Index: 38

Text #10

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1146. Min Act: -0.0002

Data Index: 1470713 (Python Code)

Max Activating Token Index: 19

Text #11

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1164. Min Act: -0.0002

Data Index: 1576611 (Python Code)

Max Activating Token Index: 403

Text #12

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1153. Min Act: -0.0002

Data Index: 1527108 (Python Code)

Max Activating Token Index: 45

Text #13

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1110. Min Act: -0.0002

Data Index: 1528704 (Python Code)

Max Activating Token Index: 14

Text #14

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1166. Min Act: -0.0002

Data Index: 1408398 (Python Code)

Max Activating Token Index: 36

Text #15

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1110. Min Act: -0.0002

Data Index: 1500066 (Python Code)

Max Activating Token Index: 29

Text #16

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1159. Min Act: -0.0002

Data Index: 1429730 (Python Code)

Max Activating Token Index: 114

Text #17

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1194. Min Act: -0.0002

Data Index: 1568160 (Python Code)

Max Activating Token Index: 98

Text #18

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1137. Min Act: -0.0002

Data Index: 1461340 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1134. Min Act: -0.0002

Data Index: 1585038 (Python Code)

Max Activating Token Index: 427