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

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

Neuron 1995 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: 0.0434. Min Range: -0.0434

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1648012 (Python Code)

Max Activating Token Index: 530

Text #1

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1484135 (Python Code)

Max Activating Token Index: 184

Text #2

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1334360 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1501136 (Python Code)

Max Activating Token Index: 863

Text #4

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0275. Min Act: -0.0002

Data Index: 607831 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0306. Min Act: -0.0002

Data Index: 968396 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0270. Min Act: -0.0002

Data Index: 537035 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0248. Min Act: -0.0002

Data Index: 617887 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0255. Min Act: -0.0002

Data Index: 1305941 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0240. Min Act: -0.0002

Data Index: 339347 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0242. Min Act: -0.0002

Data Index: 1506354 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1447405 (Python Code)

Max Activating Token Index: 271

Text #12

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1612023 (Python Code)

Max Activating Token Index: 785

Text #13

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1602163 (Python Code)

Max Activating Token Index: 754

Text #14

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1575758 (Python Code)

Max Activating Token Index: 54

Text #15

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0209. Min Act: -0.0002

Data Index: 161931 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0252. Min Act: -0.0002

Data Index: 240967 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0241. Min Act: -0.0002

Data Index: 1467880 (Python Code)

Max Activating Token Index: 206

Text #18

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0235. Min Act: -0.0002

Data Index: 253449 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0219. Min Act: -0.0002

Data Index: 1424865 (Python Code)

Max Activating Token Index: 362