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

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

Neuron 5928 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.5784. Min Act: -0.0000

Data Index: 475132 (C4 (Web Text))

Max Activating Token Index: 256

Text #1

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.5331. Min Act: -0.0000

Data Index: 596750 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.5361. Min Act: -0.0000

Data Index: 1150807 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.5511. Min Act: -0.0000

Data Index: 1234871 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.5247. Min Act: -0.0000

Data Index: 241839 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.5281. Min Act: -0.0000

Data Index: 187294 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.4831. Min Act: -0.0000

Data Index: 1330429 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.4832. Min Act: -0.0000

Data Index: 722738 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.4592. Min Act: -0.0000

Data Index: 980757 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.4979. Min Act: -0.0000

Data Index: 389984 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.4537. Min Act: -0.0000

Data Index: 1483869 (Python Code)

Max Activating Token Index: 24

Text #11

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.4373. Min Act: -0.0000

Data Index: 375641 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.4356. Min Act: -0.0000

Data Index: 1224731 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.4619. Min Act: -0.0000

Data Index: 584419 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.4193. Min Act: -0.0000

Data Index: 806779 (C4 (Web Text))

Max Activating Token Index: 510

Text #15

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.4324. Min Act: -0.0000

Data Index: 107509 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.4452. Min Act: -0.0000

Data Index: 775728 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.4306. Min Act: -0.0000

Data Index: 1162544 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.3856. Min Act: -0.0000

Data Index: 1068530 (C4 (Web Text))

Max Activating Token Index: 796

Text #19

Max Range: 0.5784. Min Range: -0.5784

Max Act: 0.4270. Min Act: -0.0000

Data Index: 1165361 (C4 (Web Text))

Max Activating Token Index: 146