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

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

Neuron 4003 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9733. Min Range: -3.9733

Max Act: 3.5031. Min Act: -0.0000

Data Index: 1162723 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 3.9733. Min Range: -3.9733

Max Act: 3.6837. Min Act: -0.0000

Data Index: 598456 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 3.9733. Min Range: -3.9733

Max Act: 3.1350. Min Act: -0.0000

Data Index: 720912 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 3.9733. Min Range: -3.9733

Max Act: 3.2986. Min Act: -0.0000

Data Index: 888889 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 3.9733. Min Range: -3.9733

Max Act: 3.3898. Min Act: -0.0000

Data Index: 1308491 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 3.9733. Min Range: -3.9733

Max Act: 3.3901. Min Act: -0.0000

Data Index: 627984 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 3.9733. Min Range: -3.9733

Max Act: 3.2038. Min Act: -0.0000

Data Index: 1287051 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 3.9733. Min Range: -3.9733

Max Act: 3.9733. Min Act: -0.0000

Data Index: 1121711 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 3.9733. Min Range: -3.9733

Max Act: 3.2499. Min Act: -0.0000

Data Index: 415219 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 3.9733. Min Range: -3.9733

Max Act: 3.2973. Min Act: -0.0000

Data Index: 793853 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 3.9733. Min Range: -3.9733

Max Act: 3.1324. Min Act: -0.0000

Data Index: 895807 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 3.9733. Min Range: -3.9733

Max Act: 3.7303. Min Act: -0.0000

Data Index: 26135 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 3.9733. Min Range: -3.9733

Max Act: 3.1988. Min Act: -0.0000

Data Index: 11197 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 3.9733. Min Range: -3.9733

Max Act: 2.8129. Min Act: -0.0000

Data Index: 15108 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 3.9733. Min Range: -3.9733

Max Act: 2.9815. Min Act: -0.0000

Data Index: 1059623 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 3.9733. Min Range: -3.9733

Max Act: 3.3023. Min Act: -0.0000

Data Index: 1278161 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 3.9733. Min Range: -3.9733

Max Act: 2.7904. Min Act: -0.0000

Data Index: 10496 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 3.9733. Min Range: -3.9733

Max Act: 3.0107. Min Act: -0.0000

Data Index: 524194 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 3.9733. Min Range: -3.9733

Max Act: 3.1634. Min Act: -0.0000

Data Index: 318246 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 3.9733. Min Range: -3.9733

Max Act: 3.1663. Min Act: -0.0000

Data Index: 921677 (C4 (Web Text))

Max Activating Token Index: 383