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

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

Neuron 3271 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: 0.1639. Min Range: -0.1639

Max Act: 0.1598. Min Act: -0.0000

Data Index: 558277 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1639. Min Act: -0.0000

Data Index: 496299 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1608. Min Act: -0.0000

Data Index: 965841 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1597. Min Act: -0.0000

Data Index: 460386 (C4 (Web Text))

Max Activating Token Index: 671

Text #4

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1567. Min Act: -0.0000

Data Index: 287961 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1542. Min Act: -0.0000

Data Index: 1292546 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1592. Min Act: -0.0000

Data Index: 212016 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1497. Min Act: -0.0000

Data Index: 898025 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1372. Min Act: -0.0000

Data Index: 321699 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1334. Min Act: -0.0000

Data Index: 447999 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1405. Min Act: -0.0000

Data Index: 287719 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1345. Min Act: -0.0000

Data Index: 1338889 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1245. Min Act: -0.0000

Data Index: 883961 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1231. Min Act: -0.0000

Data Index: 472381 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1276. Min Act: -0.0000

Data Index: 384450 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1276. Min Act: -0.0000

Data Index: 257413 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1241. Min Act: -0.0000

Data Index: 333672 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1229. Min Act: -0.0000

Data Index: 45458 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1223. Min Act: -0.0000

Data Index: 429429 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1189. Min Act: -0.0000

Data Index: 757341 (C4 (Web Text))

Max Activating Token Index: 617