Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 250 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2889. Min Act: -0.0003

Data Index: 1099535 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2931. Min Act: -0.0003

Data Index: 765790 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2632. Min Act: -0.0003

Data Index: 149251 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2518. Min Act: -0.0003

Data Index: 1303784 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2349. Min Act: -0.0003

Data Index: 1150100 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2415. Min Act: -0.0003

Data Index: 446298 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2488. Min Act: -0.0003

Data Index: 956677 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2464. Min Act: -0.0003

Data Index: 42875 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2409. Min Act: -0.0003

Data Index: 332668 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2614. Min Act: -0.0003

Data Index: 99602 (C4 (Web Text))

Max Activating Token Index: 450

Text #10

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2286. Min Act: -0.0003

Data Index: 462424 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2293. Min Act: -0.0003

Data Index: 389425 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2396. Min Act: -0.0003

Data Index: 126896 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2558. Min Act: -0.0003

Data Index: 275562 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2362. Min Act: -0.0003

Data Index: 464726 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2235. Min Act: -0.0003

Data Index: 242816 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2284. Min Act: -0.0003

Data Index: 1181691 (C4 (Web Text))

Max Activating Token Index: 263

Text #17

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2236. Min Act: -0.0004

Data Index: 317638 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2409. Min Act: -0.0003

Data Index: 246404 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2531. Min Act: -0.0003

Data Index: 737107 (C4 (Web Text))

Max Activating Token Index: 253