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

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

Neuron 4672 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: 1.0744. Min Range: -1.0744

Max Act: 1.0744. Min Act: -0.0000

Data Index: 285824 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.9470. Min Act: -0.0000

Data Index: 284381 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.9331. Min Act: -0.0000

Data Index: 423913 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.9771. Min Act: -0.0000

Data Index: 1213950 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.8943. Min Act: -0.0000

Data Index: 1319414 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.8989. Min Act: -0.0000

Data Index: 98535 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.8914. Min Act: -0.0000

Data Index: 1058504 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.8894. Min Act: -0.0000

Data Index: 1284129 (C4 (Web Text))

Max Activating Token Index: 807

Text #8

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.8792. Min Act: -0.0000

Data Index: 126630 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.7822. Min Act: -0.0000

Data Index: 699283 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.8409. Min Act: -0.0000

Data Index: 1330420 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.8366. Min Act: -0.0000

Data Index: 402211 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.8516. Min Act: -0.0000

Data Index: 1111468 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.7923. Min Act: -0.0000

Data Index: 927187 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.8349. Min Act: -0.0000

Data Index: 729677 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.8327. Min Act: -0.0000

Data Index: 53894 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.8044. Min Act: -0.0000

Data Index: 947283 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.7754. Min Act: -0.0000

Data Index: 1176474 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.7996. Min Act: -0.0000

Data Index: 55308 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 1.0744. Min Range: -1.0744

Max Act: 0.7923. Min Act: -0.0000

Data Index: 632714 (C4 (Web Text))

Max Activating Token Index: 129