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

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

Neuron 4698 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: 0.0332. Min Range: -0.0332

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1615800 (Python Code)

Max Activating Token Index: 213

Text #1

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0297. Min Act: -0.0002

Data Index: 1646920 (Python Code)

Max Activating Token Index: 703

Text #2

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1554572 (Python Code)

Max Activating Token Index: 546

Text #3

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0306. Min Act: -0.0002

Data Index: 1398618 (Python Code)

Max Activating Token Index: 766

Text #4

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0295. Min Act: -0.0002

Data Index: 434776 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0272. Min Act: -0.0002

Data Index: 1506223 (Python Code)

Max Activating Token Index: 344

Text #6

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0266. Min Act: -0.0002

Data Index: 1370455 (Python Code)

Max Activating Token Index: 608

Text #7

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0270. Min Act: -0.0002

Data Index: 299571 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1488336 (Python Code)

Max Activating Token Index: 608

Text #9

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0247. Min Act: -0.0002

Data Index: 116000 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1608905 (Python Code)

Max Activating Token Index: 297

Text #11

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1367990 (Python Code)

Max Activating Token Index: 251

Text #12

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1651260 (Python Code)

Max Activating Token Index: 305

Text #13

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1539449 (Python Code)

Max Activating Token Index: 493

Text #14

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0246. Min Act: -0.0002

Data Index: 378465 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0216. Min Act: -0.0003

Data Index: 511348 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1504577 (Python Code)

Max Activating Token Index: 740

Text #17

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0247. Min Act: -0.0002

Data Index: 1647894 (Python Code)

Max Activating Token Index: 621

Text #18

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0231. Min Act: -0.0002

Data Index: 931885 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0259. Min Act: -0.0002

Data Index: 1475772 (Python Code)

Max Activating Token Index: 869