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

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

Neuron 542 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: 2.1251. Min Range: -2.1251

Max Act: 2.1251. Min Act: -0.0000

Data Index: 1381634 (Python Code)

Max Activating Token Index: 914

Text #1

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.9751. Min Act: -0.0000

Data Index: 1451851 (Python Code)

Max Activating Token Index: 982

Text #2

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.9837. Min Act: -0.0000

Data Index: 1453356 (Python Code)

Max Activating Token Index: 913

Text #3

Max Range: 2.1251. Min Range: -2.1251

Max Act: 2.0857. Min Act: -0.0000

Data Index: 1411634 (Python Code)

Max Activating Token Index: 901

Text #4

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.7368. Min Act: -0.0000

Data Index: 1416930 (Python Code)

Max Activating Token Index: 620

Text #5

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.7364. Min Act: -0.0000

Data Index: 1499519 (Python Code)

Max Activating Token Index: 171

Text #6

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.8506. Min Act: -0.0000

Data Index: 1032327 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.7201. Min Act: -0.0000

Data Index: 635009 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.6455. Min Act: -0.0000

Data Index: 1498254 (Python Code)

Max Activating Token Index: 187

Text #9

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.7041. Min Act: -0.0000

Data Index: 1621065 (Python Code)

Max Activating Token Index: 956

Text #10

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.7127. Min Act: -0.0000

Data Index: 1432731 (Python Code)

Max Activating Token Index: 232

Text #11

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.5895. Min Act: -0.0000

Data Index: 1085336 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.4217. Min Act: -0.0000

Data Index: 669616 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.5015. Min Act: -0.0001

Data Index: 1503936 (Python Code)

Max Activating Token Index: 312

Text #14

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.5334. Min Act: -0.0000

Data Index: 1500349 (Python Code)

Max Activating Token Index: 686

Text #15

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.4765. Min Act: -0.0000

Data Index: 1471414 (Python Code)

Max Activating Token Index: 915

Text #16

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.4907. Min Act: -0.0000

Data Index: 1464582 (Python Code)

Max Activating Token Index: 831

Text #17

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.4921. Min Act: -0.0000

Data Index: 1501152 (Python Code)

Max Activating Token Index: 148

Text #18

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.5574. Min Act: -0.0000

Data Index: 1240205 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 2.1251. Min Range: -2.1251

Max Act: 1.5096. Min Act: -0.0000

Data Index: 377191 (C4 (Web Text))

Max Activating Token Index: 29