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

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

Neuron 2228 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2409. Min Act: -0.0001

Data Index: 498953 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2523. Min Act: -0.0001

Data Index: 331231 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2671. Min Act: -0.0001

Data Index: 324779 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2308. Min Act: -0.0001

Data Index: 971180 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2376. Min Act: -0.0001

Data Index: 873176 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2512. Min Act: -0.0000

Data Index: 585829 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2370. Min Act: -0.0001

Data Index: 322542 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2190. Min Act: -0.0001

Data Index: 574922 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2239. Min Act: -0.0001

Data Index: 730594 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2480. Min Act: -0.0001

Data Index: 17776 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2230. Min Act: -0.0001

Data Index: 112711 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2286. Min Act: -0.0001

Data Index: 1353465 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2276. Min Act: -0.0001

Data Index: 1174639 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2351. Min Act: -0.0001

Data Index: 1003443 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2201. Min Act: -0.0001

Data Index: 773126 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2288. Min Act: -0.0001

Data Index: 620027 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2266. Min Act: -0.0001

Data Index: 336550 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2262. Min Act: -0.0001

Data Index: 999276 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2267. Min Act: -0.0001

Data Index: 387724 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.2671. Min Range: -0.2671

Max Act: 0.2110. Min Act: -0.0001

Data Index: 841166 (C4 (Web Text))

Max Activating Token Index: 166