Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 613 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0399. Min Act: -0.0004

Data Index: 88016 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0370. Min Act: -0.0003

Data Index: 701799 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0335. Min Act: -0.0003

Data Index: 488256 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0334. Min Act: -0.0003

Data Index: 307164 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0325. Min Act: -0.0003

Data Index: 714599 (C4 (Web Text))

Max Activating Token Index: 963

Text #5

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0331. Min Act: -0.0003

Data Index: 875814 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0325. Min Act: -0.0003

Data Index: 229490 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0317. Min Act: -0.0003

Data Index: 1307565 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0323. Min Act: -0.0003

Data Index: 856588 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0316. Min Act: -0.0003

Data Index: 1017872 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0317. Min Act: -0.0003

Data Index: 460135 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0320. Min Act: -0.0003

Data Index: 193657 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0311. Min Act: -0.0003

Data Index: 292818 (C4 (Web Text))

Max Activating Token Index: 457

Text #13

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0324. Min Act: -0.0003

Data Index: 846354 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0317. Min Act: -0.0003

Data Index: 716884 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0306. Min Act: -0.0004

Data Index: 98620 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1103817 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0301. Min Act: -0.0003

Data Index: 818711 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0297. Min Act: -0.0003

Data Index: 315620 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.0399. Min Range: -0.0399

Max Act: 0.0288. Min Act: -0.0003

Data Index: 43818 (C4 (Web Text))

Max Activating Token Index: 314