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

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

Neuron 617 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0399. Min Act: -0.0001

Data Index: 977341 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0392. Min Act: -0.0001

Data Index: 352648 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0417. Min Act: -0.0001

Data Index: 977125 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0335. Min Act: -0.0001

Data Index: 1007626 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0329. Min Act: -0.0001

Data Index: 1267530 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0332. Min Act: -0.0001

Data Index: 929050 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0334. Min Act: -0.0001

Data Index: 1415315 (Python Code)

Max Activating Token Index: 410

Text #7

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0343. Min Act: -0.0001

Data Index: 582289 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0319. Min Act: -0.0001

Data Index: 190474 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0327. Min Act: -0.0001

Data Index: 393842 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0333. Min Act: -0.0001

Data Index: 962884 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0322. Min Act: -0.0001

Data Index: 316301 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0314. Min Act: -0.0001

Data Index: 795632 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0328. Min Act: -0.0001

Data Index: 990158 (C4 (Web Text))

Max Activating Token Index: 270

Text #14

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0311. Min Act: -0.0001

Data Index: 1396318 (Python Code)

Max Activating Token Index: 57

Text #15

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0327. Min Act: -0.0001

Data Index: 944309 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0315. Min Act: -0.0001

Data Index: 722813 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0316. Min Act: -0.0001

Data Index: 272835 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0315. Min Act: -0.0001

Data Index: 781318 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.0417. Min Range: -0.0417

Max Act: 0.0324. Min Act: -0.0001

Data Index: 155760 (C4 (Web Text))

Max Activating Token Index: 190