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

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

Neuron 122 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: 0.3221. Min Range: -0.3221

Max Act: 0.3221. Min Act: -0.0000

Data Index: 1475418 (Python Code)

Max Activating Token Index: 328

Text #1

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1543244 (Python Code)

Max Activating Token Index: 137

Text #2

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2801. Min Act: -0.0000

Data Index: 1378617 (Python Code)

Max Activating Token Index: 121

Text #3

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2469. Min Act: -0.0000

Data Index: 1599043 (Python Code)

Max Activating Token Index: 65

Text #4

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2544. Min Act: -0.0000

Data Index: 1441257 (Python Code)

Max Activating Token Index: 110

Text #5

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2606. Min Act: -0.0000

Data Index: 1628577 (Python Code)

Max Activating Token Index: 264

Text #6

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2244. Min Act: -0.0000

Data Index: 1492662 (Python Code)

Max Activating Token Index: 242

Text #7

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2532. Min Act: -0.0000

Data Index: 1549876 (Python Code)

Max Activating Token Index: 213

Text #8

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1410137 (Python Code)

Max Activating Token Index: 177

Text #9

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2448. Min Act: -0.0000

Data Index: 1549179 (Python Code)

Max Activating Token Index: 206

Text #10

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2341. Min Act: -0.0000

Data Index: 1582462 (Python Code)

Max Activating Token Index: 302

Text #11

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1526418 (Python Code)

Max Activating Token Index: 65

Text #12

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1598705 (Python Code)

Max Activating Token Index: 272

Text #13

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2239. Min Act: -0.0000

Data Index: 1366913 (Python Code)

Max Activating Token Index: 104

Text #14

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2230. Min Act: -0.0000

Data Index: 1436360 (Python Code)

Max Activating Token Index: 443

Text #15

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2132. Min Act: -0.0000

Data Index: 1394793 (Python Code)

Max Activating Token Index: 926

Text #16

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1410700 (Python Code)

Max Activating Token Index: 80

Text #17

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2138. Min Act: -0.0000

Data Index: 1414890 (Python Code)

Max Activating Token Index: 466

Text #18

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2279. Min Act: -0.0000

Data Index: 1631301 (Python Code)

Max Activating Token Index: 151

Text #19

Max Range: 0.3221. Min Range: -0.3221

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1630849 (Python Code)

Max Activating Token Index: 155