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

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

Neuron 473 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: 1.4692. Min Range: -1.4692

Max Act: 1.4692. Min Act: -0.0000

Data Index: 1245496 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.2783. Min Act: -0.0001

Data Index: 715319 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.3056. Min Act: -0.0000

Data Index: 1393627 (Python Code)

Max Activating Token Index: 212

Text #3

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.2780. Min Act: -0.0001

Data Index: 777714 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.1683. Min Act: -0.0001

Data Index: 793778 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.1694. Min Act: -0.0001

Data Index: 1332063 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.3522. Min Act: -0.0000

Data Index: 368744 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.2110. Min Act: -0.0001

Data Index: 254638 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.1796. Min Act: -0.0001

Data Index: 35939 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.1337. Min Act: -0.0001

Data Index: 691947 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.2322. Min Act: -0.0001

Data Index: 1167240 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.1817. Min Act: -0.0001

Data Index: 1539738 (Python Code)

Max Activating Token Index: 461

Text #12

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.1518. Min Act: -0.0001

Data Index: 313134 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 1.4692. Min Range: -1.4692

Max Act: 0.9804. Min Act: -0.0001

Data Index: 1358733 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.0901. Min Act: -0.0000

Data Index: 1154099 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.1010. Min Act: -0.0001

Data Index: 1333461 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.1962. Min Act: -0.0001

Data Index: 150759 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.0399. Min Act: -0.0000

Data Index: 779021 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 1.4692. Min Range: -1.4692

Max Act: 1.1847. Min Act: -0.0001

Data Index: 757565 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 1.4692. Min Range: -1.4692

Max Act: 0.9906. Min Act: -0.0001

Data Index: 463129 (C4 (Web Text))

Max Activating Token Index: 636