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

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

Neuron 2048 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: 2.0361. Min Range: -2.0361

Max Act: 2.0361. Min Act: -0.0000

Data Index: 1198322 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 2.0361. Min Range: -2.0361

Max Act: 1.8602. Min Act: -0.0000

Data Index: 634758 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 2.0361. Min Range: -2.0361

Max Act: 1.8804. Min Act: -0.0000

Data Index: 291492 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 2.0361. Min Range: -2.0361

Max Act: 1.8210. Min Act: -0.0000

Data Index: 1164484 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 2.0361. Min Range: -2.0361

Max Act: 1.6099. Min Act: -0.0000

Data Index: 1092113 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 2.0361. Min Range: -2.0361

Max Act: 1.5209. Min Act: -0.0000

Data Index: 215425 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 2.0361. Min Range: -2.0361

Max Act: 1.5625. Min Act: -0.0000

Data Index: 123758 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 2.0361. Min Range: -2.0361

Max Act: 1.5278. Min Act: -0.0000

Data Index: 446276 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 2.0361. Min Range: -2.0361

Max Act: 1.3527. Min Act: -0.0000

Data Index: 14027 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 2.0361. Min Range: -2.0361

Max Act: 1.4287. Min Act: -0.0000

Data Index: 732385 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 2.0361. Min Range: -2.0361

Max Act: 1.4521. Min Act: -0.0000

Data Index: 1246396 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 2.0361. Min Range: -2.0361

Max Act: 1.3676. Min Act: -0.0000

Data Index: 103551 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 2.0361. Min Range: -2.0361

Max Act: 1.3681. Min Act: -0.0000

Data Index: 739166 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 2.0361. Min Range: -2.0361

Max Act: 1.2247. Min Act: -0.0000

Data Index: 481091 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 2.0361. Min Range: -2.0361

Max Act: 1.3358. Min Act: -0.0000

Data Index: 1086256 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 2.0361. Min Range: -2.0361

Max Act: 1.3282. Min Act: -0.0000

Data Index: 271510 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 2.0361. Min Range: -2.0361

Max Act: 1.3683. Min Act: -0.0000

Data Index: 395174 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 2.0361. Min Range: -2.0361

Max Act: 1.2490. Min Act: -0.0000

Data Index: 1078549 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 2.0361. Min Range: -2.0361

Max Act: 1.3122. Min Act: -0.0000

Data Index: 108569 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 2.0361. Min Range: -2.0361

Max Act: 1.3386. Min Act: -0.0000

Data Index: 1354359 (C4 (Web Text))

Max Activating Token Index: 180