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

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

Neuron 967 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0324. Min Act: -0.0001

Data Index: 537047 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1357062 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0285. Min Act: -0.0001

Data Index: 1563018 (Python Code)

Max Activating Token Index: 392

Text #3

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0262. Min Act: -0.0001

Data Index: 182379 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0259. Min Act: -0.0001

Data Index: 1240693 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0246. Min Act: -0.0001

Data Index: 404179 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0264. Min Act: -0.0001

Data Index: 11651 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0260. Min Act: -0.0001

Data Index: 1655129 (Python Code)

Max Activating Token Index: 714

Text #8

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0235. Min Act: -0.0001

Data Index: 233564 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0227. Min Act: -0.0001

Data Index: 983622 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0246. Min Act: -0.0001

Data Index: 1006888 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0239. Min Act: -0.0002

Data Index: 241410 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0225. Min Act: -0.0002

Data Index: 289477 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0229. Min Act: -0.0001

Data Index: 794905 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0221. Min Act: -0.0002

Data Index: 116592 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0240. Min Act: -0.0002

Data Index: 178983 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0234. Min Act: -0.0001

Data Index: 1540826 (Python Code)

Max Activating Token Index: 389

Text #17

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0216. Min Act: -0.0002

Data Index: 735027 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0227. Min Act: -0.0001

Data Index: 1621468 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0324. Min Range: -0.0324

Max Act: 0.0236. Min Act: -0.0002

Data Index: 575932 (C4 (Web Text))

Max Activating Token Index: 137