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

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

Neuron 3533 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4359. Min Range: -1.4359

Max Act: 1.4359. Min Act: -0.0000

Data Index: 1003799 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 1.4359. Min Range: -1.4359

Max Act: 1.3877. Min Act: -0.0000

Data Index: 1293958 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 1.4359. Min Range: -1.4359

Max Act: 1.4138. Min Act: -0.0000

Data Index: 414790 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 1.4359. Min Range: -1.4359

Max Act: 1.3669. Min Act: -0.0000

Data Index: 153440 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 1.4359. Min Range: -1.4359

Max Act: 1.2506. Min Act: -0.0000

Data Index: 649360 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 1.4359. Min Range: -1.4359

Max Act: 1.2231. Min Act: -0.0000

Data Index: 136631 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 1.4359. Min Range: -1.4359

Max Act: 1.2838. Min Act: -0.0001

Data Index: 574286 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 1.4359. Min Range: -1.4359

Max Act: 1.2187. Min Act: -0.0000

Data Index: 75588 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 1.4359. Min Range: -1.4359

Max Act: 1.1803. Min Act: -0.0000

Data Index: 442432 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 1.4359. Min Range: -1.4359

Max Act: 1.2187. Min Act: -0.0000

Data Index: 1316462 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 1.4359. Min Range: -1.4359

Max Act: 1.1773. Min Act: -0.0000

Data Index: 557677 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 1.4359. Min Range: -1.4359

Max Act: 1.2417. Min Act: -0.0000

Data Index: 232044 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 1.4359. Min Range: -1.4359

Max Act: 1.1506. Min Act: -0.0000

Data Index: 918466 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 1.4359. Min Range: -1.4359

Max Act: 1.1443. Min Act: -0.0000

Data Index: 576047 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 1.4359. Min Range: -1.4359

Max Act: 1.1896. Min Act: -0.0000

Data Index: 355940 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 1.4359. Min Range: -1.4359

Max Act: 1.2113. Min Act: -0.0000

Data Index: 588128 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 1.4359. Min Range: -1.4359

Max Act: 1.1806. Min Act: -0.0000

Data Index: 74668 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 1.4359. Min Range: -1.4359

Max Act: 1.1707. Min Act: -0.0000

Data Index: 1270056 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 1.4359. Min Range: -1.4359

Max Act: 1.0731. Min Act: -0.0000

Data Index: 398767 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 1.4359. Min Range: -1.4359

Max Act: 1.1259. Min Act: -0.0000

Data Index: 889315 (C4 (Web Text))

Max Activating Token Index: 573