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

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

Neuron 4684 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: 0.1857. Min Range: -0.1857

Max Act: 0.1857. Min Act: -0.0000

Data Index: 772442 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1606. Min Act: -0.0000

Data Index: 256500 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1668. Min Act: -0.0000

Data Index: 925352 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1379. Min Act: -0.0000

Data Index: 271329 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1734. Min Act: -0.0000

Data Index: 503882 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1484. Min Act: -0.0000

Data Index: 592977 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1502. Min Act: -0.0000

Data Index: 1090017 (C4 (Web Text))

Max Activating Token Index: 634

Text #7

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1382. Min Act: -0.0000

Data Index: 754589 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1434. Min Act: -0.0000

Data Index: 693688 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1264. Min Act: -0.0000

Data Index: 1143173 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1366. Min Act: -0.0000

Data Index: 594455 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1621. Min Act: -0.0000

Data Index: 383595 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1497. Min Act: -0.0000

Data Index: 81216 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1082222 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1478. Min Act: -0.0000

Data Index: 862327 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1412. Min Act: -0.0000

Data Index: 98098 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1175. Min Act: -0.0000

Data Index: 1273808 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1084. Min Act: -0.0000

Data Index: 751095 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1358. Min Act: -0.0000

Data Index: 440758 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 0.1857. Min Range: -0.1857

Max Act: 0.1422. Min Act: -0.0000

Data Index: 1021297 (C4 (Web Text))

Max Activating Token Index: 207