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

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

Neuron 2926 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1282. Min Range: -1.1282

Max Act: 1.1246. Min Act: -0.0000

Data Index: 343597 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 1.1282. Min Range: -1.1282

Max Act: 1.0370. Min Act: 0.0001

Data Index: 27032 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 1.1282. Min Range: -1.1282

Max Act: 1.1282. Min Act: -0.0000

Data Index: 634699 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.8654. Min Act: 0.0000

Data Index: 311832 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.8446. Min Act: 0.0000

Data Index: 839825 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.7812. Min Act: -0.0000

Data Index: 888355 (C4 (Web Text))

Max Activating Token Index: 116

Text #6

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.7165. Min Act: 0.0000

Data Index: 1208457 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.6430. Min Act: -0.0000

Data Index: 487196 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.5921. Min Act: -0.0000

Data Index: 76549 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.6245. Min Act: 0.0000

Data Index: 1306434 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.6000. Min Act: 0.0000

Data Index: 628526 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.6015. Min Act: -0.0000

Data Index: 159589 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.5625. Min Act: -0.0000

Data Index: 372931 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.6326. Min Act: 0.0000

Data Index: 625734 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.5966. Min Act: 0.0000

Data Index: 439027 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.5738. Min Act: 0.0000

Data Index: 1233998 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.5730. Min Act: -0.0000

Data Index: 760139 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.5985. Min Act: 0.0000

Data Index: 469744 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.5418. Min Act: 0.0000

Data Index: 1203156 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 1.1282. Min Range: -1.1282

Max Act: 0.5640. Min Act: -0.0000

Data Index: 442501 (C4 (Web Text))

Max Activating Token Index: 636