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

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

Neuron 3468 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7588. Min Range: -3.7588

Max Act: 3.7588. Min Act: -0.0000

Data Index: 41804 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 3.7588. Min Range: -3.7588

Max Act: 3.5043. Min Act: -0.0000

Data Index: 750179 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 3.7588. Min Range: -3.7588

Max Act: 3.4275. Min Act: -0.0000

Data Index: 1347462 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 3.7588. Min Range: -3.7588

Max Act: 3.3990. Min Act: -0.0000

Data Index: 923465 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 3.7588. Min Range: -3.7588

Max Act: 3.2286. Min Act: -0.0000

Data Index: 801665 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 3.7588. Min Range: -3.7588

Max Act: 3.5420. Min Act: -0.0000

Data Index: 886083 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 3.7588. Min Range: -3.7588

Max Act: 3.1969. Min Act: -0.0000

Data Index: 954066 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 3.7588. Min Range: -3.7588

Max Act: 3.1379. Min Act: -0.0000

Data Index: 1139443 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 3.7588. Min Range: -3.7588

Max Act: 3.1821. Min Act: -0.0000

Data Index: 714616 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 3.7588. Min Range: -3.7588

Max Act: 3.0358. Min Act: -0.0000

Data Index: 1273685 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 3.7588. Min Range: -3.7588

Max Act: 3.1359. Min Act: -0.0000

Data Index: 261497 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 3.7588. Min Range: -3.7588

Max Act: 2.7542. Min Act: -0.0000

Data Index: 1224347 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 3.7588. Min Range: -3.7588

Max Act: 2.8592. Min Act: -0.0000

Data Index: 878061 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 3.7588. Min Range: -3.7588

Max Act: 2.6740. Min Act: -0.0000

Data Index: 837732 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 3.7588. Min Range: -3.7588

Max Act: 2.7677. Min Act: -0.0000

Data Index: 1315757 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 3.7588. Min Range: -3.7588

Max Act: 2.6710. Min Act: -0.0000

Data Index: 802060 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 3.7588. Min Range: -3.7588

Max Act: 2.6349. Min Act: -0.0000

Data Index: 182012 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 3.7588. Min Range: -3.7588

Max Act: 2.5929. Min Act: -0.0000

Data Index: 385855 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 3.7588. Min Range: -3.7588

Max Act: 2.4812. Min Act: -0.0000

Data Index: 1026123 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 3.7588. Min Range: -3.7588

Max Act: 2.5901. Min Act: -0.0000

Data Index: 813547 (C4 (Web Text))

Max Activating Token Index: 214