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

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

Neuron 1501 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.3365. Min Act: -0.0000

Data Index: 1334271 (C4 (Web Text))

Max Activating Token Index: 569

Text #1

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2803. Min Act: -0.0000

Data Index: 627585 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2558. Min Act: -0.0000

Data Index: 712421 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2676. Min Act: -0.0000

Data Index: 81929 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2556. Min Act: -0.0000

Data Index: 1324790 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2447. Min Act: -0.0000

Data Index: 722517 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2396. Min Act: -0.0000

Data Index: 943788 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2461. Min Act: -0.0000

Data Index: 1273442 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2536. Min Act: -0.0000

Data Index: 643893 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2516. Min Act: -0.0000

Data Index: 996485 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2339. Min Act: -0.0000

Data Index: 844576 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1333135 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2265. Min Act: -0.0000

Data Index: 268660 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2316. Min Act: -0.0000

Data Index: 812141 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2241. Min Act: -0.0000

Data Index: 1224844 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2288. Min Act: -0.0000

Data Index: 2219 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2394. Min Act: -0.0000

Data Index: 32894 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2296. Min Act: -0.0000

Data Index: 914248 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2281. Min Act: -0.0000

Data Index: 698224 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.3365. Min Range: -0.3365

Max Act: 0.2250. Min Act: -0.0000

Data Index: 73547 (C4 (Web Text))

Max Activating Token Index: 325