Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3737 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1868. Min Act: -0.0000

Data Index: 1214881 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1708. Min Act: -0.0000

Data Index: 1179928 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1609. Min Act: -0.0000

Data Index: 50765 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1393. Min Act: -0.0000

Data Index: 148204 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1213. Min Act: -0.0000

Data Index: 141067 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1331. Min Act: -0.0000

Data Index: 808603 (C4 (Web Text))

Max Activating Token Index: 712

Text #6

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1336. Min Act: -0.0000

Data Index: 914222 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1417. Min Act: -0.0000

Data Index: 512867 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1355. Min Act: -0.0001

Data Index: 1573738 (Python Code)

Max Activating Token Index: 338

Text #9

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1279. Min Act: -0.0000

Data Index: 1203239 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1378. Min Act: -0.0000

Data Index: 73413 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1271. Min Act: -0.0000

Data Index: 1083021 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1263. Min Act: -0.0000

Data Index: 237279 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1206. Min Act: -0.0001

Data Index: 934450 (C4 (Web Text))

Max Activating Token Index: 523

Text #14

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1175. Min Act: -0.0001

Data Index: 1640861 (Python Code)

Max Activating Token Index: 836

Text #15

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1104. Min Act: -0.0000

Data Index: 1263399 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1169. Min Act: -0.0000

Data Index: 350310 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1205. Min Act: -0.0000

Data Index: 1311482 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1196. Min Act: -0.0000

Data Index: 1222003 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.1868. Min Range: -0.1868

Max Act: 0.1145. Min Act: -0.0000

Data Index: 227347 (C4 (Web Text))

Max Activating Token Index: 673