Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3626 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1557. Min Range: -1.1557

Max Act: 1.1557. Min Act: -0.0001

Data Index: 1152683 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 1.1557. Min Range: -1.1557

Max Act: 1.0671. Min Act: -0.0001

Data Index: 234117 (C4 (Web Text))

Max Activating Token Index: 650

Text #2

Max Range: 1.1557. Min Range: -1.1557

Max Act: 1.0828. Min Act: -0.0001

Data Index: 88227 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 1.1557. Min Range: -1.1557

Max Act: 1.0780. Min Act: -0.0001

Data Index: 202543 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 1.1557. Min Range: -1.1557

Max Act: 1.0408. Min Act: -0.0001

Data Index: 264185 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 1.1557. Min Range: -1.1557

Max Act: 1.0092. Min Act: -0.0001

Data Index: 1297550 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 1.1557. Min Range: -1.1557

Max Act: 1.0389. Min Act: -0.0001

Data Index: 352765 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.9861. Min Act: -0.0001

Data Index: 915305 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.9870. Min Act: -0.0001

Data Index: 916986 (C4 (Web Text))

Max Activating Token Index: 205

Text #9

Max Range: 1.1557. Min Range: -1.1557

Max Act: 1.0097. Min Act: -0.0001

Data Index: 953069 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.9965. Min Act: -0.0001

Data Index: 509456 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.9987. Min Act: -0.0001

Data Index: 129879 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.9919. Min Act: -0.0001

Data Index: 381757 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.9594. Min Act: -0.0001

Data Index: 1118058 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.9622. Min Act: -0.0001

Data Index: 778178 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.9879. Min Act: -0.0001

Data Index: 99399 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.9538. Min Act: -0.0001

Data Index: 751138 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.9523. Min Act: -0.0001

Data Index: 286235 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.9690. Min Act: -0.0001

Data Index: 1038789 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 1.1557. Min Range: -1.1557

Max Act: 0.9385. Min Act: -0.0001

Data Index: 482975 (C4 (Web Text))

Max Activating Token Index: 933