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

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

Neuron 1066 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: 0.0465. Min Range: -0.0465

Max Act: 0.0465. Min Act: -0.0003

Data Index: 150226 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0461. Min Act: -0.0002

Data Index: 142045 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0416. Min Act: -0.0003

Data Index: 1299793 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0418. Min Act: -0.0003

Data Index: 986498 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0420. Min Act: -0.0003

Data Index: 964114 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0396. Min Act: -0.0003

Data Index: 439237 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0376. Min Act: -0.0003

Data Index: 1095188 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1209022 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0346. Min Act: -0.0002

Data Index: 255197 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0353. Min Act: -0.0003

Data Index: 1035765 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0351. Min Act: -0.0003

Data Index: 872554 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0344. Min Act: -0.0003

Data Index: 261508 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0328. Min Act: -0.0004

Data Index: 153503 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0336. Min Act: -0.0003

Data Index: 427629 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0322. Min Act: -0.0003

Data Index: 717596 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1063180 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0315. Min Act: -0.0003

Data Index: 721907 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0317. Min Act: -0.0003

Data Index: 972861 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0314. Min Act: -0.0002

Data Index: 65805 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 0.0465. Min Range: -0.0465

Max Act: 0.0319. Min Act: -0.0003

Data Index: 445700 (C4 (Web Text))

Max Activating Token Index: 279