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

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

Neuron 1057 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: 0.0287. Min Range: -0.0287

Max Act: 0.0287. Min Act: -0.0003

Data Index: 96962 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0277. Min Act: -0.0003

Data Index: 38733 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0262. Min Act: -0.0003

Data Index: 309025 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0268. Min Act: -0.0003

Data Index: 273993 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1552446 (Python Code)

Max Activating Token Index: 1011

Text #5

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0258. Min Act: -0.0003

Data Index: 1655697 (Python Code)

Max Activating Token Index: 780

Text #6

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0251. Min Act: -0.0003

Data Index: 1240037 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0254. Min Act: -0.0003

Data Index: 1129648 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1230600 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0242. Min Act: -0.0003

Data Index: 337143 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0233. Min Act: -0.0003

Data Index: 426480 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0240. Min Act: -0.0003

Data Index: 568523 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0227. Min Act: -0.0003

Data Index: 384893 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0235. Min Act: -0.0003

Data Index: 113246 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0228. Min Act: -0.0003

Data Index: 182168 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0227. Min Act: -0.0004

Data Index: 328414 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0227. Min Act: -0.0003

Data Index: 818705 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0224. Min Act: -0.0003

Data Index: 206105 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0223. Min Act: -0.0004

Data Index: 1077150 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0226. Min Act: -0.0003

Data Index: 335958 (C4 (Web Text))

Max Activating Token Index: 652