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

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

Neuron 3749 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: 1.5334. Min Range: -1.5334

Max Act: 1.5334. Min Act: -0.0000

Data Index: 227387 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.5140. Min Act: -0.0000

Data Index: 93126 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.5098. Min Act: -0.0000

Data Index: 588258 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.4260. Min Act: -0.0000

Data Index: 358057 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.4183. Min Act: -0.0000

Data Index: 921322 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.4618. Min Act: -0.0000

Data Index: 353573 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.3511. Min Act: -0.0000

Data Index: 21036 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.3342. Min Act: -0.0000

Data Index: 1299432 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.3043. Min Act: -0.0000

Data Index: 1238976 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.1982. Min Act: -0.0000

Data Index: 50456 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.1795. Min Act: -0.0000

Data Index: 458322 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.2594. Min Act: -0.0000

Data Index: 1197886 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.2267. Min Act: -0.0000

Data Index: 8174 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.1659. Min Act: -0.0000

Data Index: 162496 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.1142. Min Act: -0.0000

Data Index: 1234771 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.1370. Min Act: -0.0000

Data Index: 952383 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.1317. Min Act: -0.0001

Data Index: 847499 (C4 (Web Text))

Max Activating Token Index: 772

Text #17

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.0709. Min Act: -0.0000

Data Index: 176487 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.0440. Min Act: -0.0000

Data Index: 936782 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 1.5334. Min Range: -1.5334

Max Act: 1.1024. Min Act: -0.0000

Data Index: 889565 (C4 (Web Text))

Max Activating Token Index: 484