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

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

Neuron 3518 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.5386. Min Act: -0.0000

Data Index: 635705 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.4124. Min Act: -0.0000

Data Index: 1137081 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.4717. Min Act: -0.0000

Data Index: 555762 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.4275. Min Act: -0.0000

Data Index: 36294 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.4308. Min Act: -0.0000

Data Index: 552788 (C4 (Web Text))

Max Activating Token Index: 446

Text #5

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.3523. Min Act: -0.0000

Data Index: 994624 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.2225. Min Act: -0.0000

Data Index: 1033255 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.2509. Min Act: -0.0000

Data Index: 1266170 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.2645. Min Act: -0.0000

Data Index: 562965 (C4 (Web Text))

Max Activating Token Index: 857

Text #9

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.2325. Min Act: -0.0000

Data Index: 738773 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.2170. Min Act: -0.0000

Data Index: 289714 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.2119. Min Act: -0.0000

Data Index: 937292 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.1434. Min Act: -0.0000

Data Index: 404782 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.1228. Min Act: -0.0000

Data Index: 110148 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.1245. Min Act: -0.0000

Data Index: 373016 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.2299. Min Act: -0.0000

Data Index: 721499 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.1392. Min Act: -0.0000

Data Index: 225165 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.1203. Min Act: -0.0000

Data Index: 478140 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.1788. Min Act: -0.0000

Data Index: 636988 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 1.5386. Min Range: -1.5386

Max Act: 1.1150. Min Act: -0.0000

Data Index: 96575 (C4 (Web Text))

Max Activating Token Index: 970