Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3690 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4620. Min Range: -1.4620

Max Act: 1.4620. Min Act: -0.0001

Data Index: 61824 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 1.4620. Min Range: -1.4620

Max Act: 1.3065. Min Act: -0.0001

Data Index: 687039 (C4 (Web Text))

Max Activating Token Index: 834

Text #2

Max Range: 1.4620. Min Range: -1.4620

Max Act: 1.2266. Min Act: -0.0001

Data Index: 906798 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 1.4620. Min Range: -1.4620

Max Act: 1.3513. Min Act: -0.0000

Data Index: 1336185 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 1.4620. Min Range: -1.4620

Max Act: 1.2149. Min Act: -0.0000

Data Index: 49434 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 1.4620. Min Range: -1.4620

Max Act: 1.1690. Min Act: -0.0000

Data Index: 636225 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 1.4620. Min Range: -1.4620

Max Act: 1.2546. Min Act: -0.0001

Data Index: 127711 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 1.4620. Min Range: -1.4620

Max Act: 1.0679. Min Act: -0.0000

Data Index: 208784 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 1.4620. Min Range: -1.4620

Max Act: 0.9915. Min Act: -0.0000

Data Index: 1261556 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 1.4620. Min Range: -1.4620

Max Act: 1.1100. Min Act: -0.0000

Data Index: 1081034 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 1.4620. Min Range: -1.4620

Max Act: 1.0911. Min Act: -0.0000

Data Index: 83900 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 1.4620. Min Range: -1.4620

Max Act: 1.0033. Min Act: -0.0000

Data Index: 482619 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 1.4620. Min Range: -1.4620

Max Act: 1.0745. Min Act: -0.0000

Data Index: 1179413 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 1.4620. Min Range: -1.4620

Max Act: 0.9311. Min Act: -0.0000

Data Index: 592567 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 1.4620. Min Range: -1.4620

Max Act: 1.0770. Min Act: -0.0000

Data Index: 138415 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 1.4620. Min Range: -1.4620

Max Act: 1.0338. Min Act: -0.0001

Data Index: 981831 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 1.4620. Min Range: -1.4620

Max Act: 1.1670. Min Act: -0.0000

Data Index: 1053040 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 1.4620. Min Range: -1.4620

Max Act: 0.9694. Min Act: -0.0000

Data Index: 268741 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 1.4620. Min Range: -1.4620

Max Act: 1.0841. Min Act: -0.0000

Data Index: 1399685 (Python Code)

Max Activating Token Index: 906

Text #19

Max Range: 1.4620. Min Range: -1.4620

Max Act: 1.0609. Min Act: -0.0000

Data Index: 1140990 (C4 (Web Text))

Max Activating Token Index: 244