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

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

Neuron 4213 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.3308. Min Act: -0.0000

Data Index: 712940 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.3378. Min Act: -0.0000

Data Index: 151608 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.2222. Min Act: -0.0000

Data Index: 476399 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.2595. Min Act: -0.0000

Data Index: 401373 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.2237. Min Act: -0.0000

Data Index: 3920 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.2172. Min Act: -0.0000

Data Index: 441487 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.1336. Min Act: -0.0000

Data Index: 681280 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.1068. Min Act: -0.0000

Data Index: 237196 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.1715. Min Act: -0.0000

Data Index: 1386141 (Python Code)

Max Activating Token Index: 344

Text #9

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.0176. Min Act: -0.0000

Data Index: 726230 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.0999. Min Act: -0.0000

Data Index: 1567034 (Python Code)

Max Activating Token Index: 291

Text #11

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.1932. Min Act: -0.0000

Data Index: 1647258 (Python Code)

Max Activating Token Index: 642

Text #12

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.0999. Min Act: -0.0000

Data Index: 647183 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.1072. Min Act: -0.0000

Data Index: 1492878 (Python Code)

Max Activating Token Index: 616

Text #14

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.0325. Min Act: -0.0000

Data Index: 904659 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 1.3378. Min Range: -1.3378

Max Act: 0.9704. Min Act: -0.0000

Data Index: 1302907 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 1.3378. Min Range: -1.3378

Max Act: 0.9795. Min Act: -0.0000

Data Index: 107453 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.0971. Min Act: -0.0000

Data Index: 313032 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.1190. Min Act: -0.0000

Data Index: 1548650 (Python Code)

Max Activating Token Index: 288

Text #19

Max Range: 1.3378. Min Range: -1.3378

Max Act: 1.0743. Min Act: -0.0000

Data Index: 1490969 (Python Code)

Max Activating Token Index: 936