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

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

Neuron 4369 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0734. Min Act: -0.0002

Data Index: 290040 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0647. Min Act: -0.0002

Data Index: 201410 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0663. Min Act: -0.0002

Data Index: 405970 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0662. Min Act: -0.0002

Data Index: 1213968 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0681. Min Act: -0.0002

Data Index: 65328 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0670. Min Act: -0.0002

Data Index: 1317623 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0640. Min Act: -0.0002

Data Index: 822923 (C4 (Web Text))

Max Activating Token Index: 65

Text #7

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1103031 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0602. Min Act: -0.0002

Data Index: 38537 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0588. Min Act: -0.0002

Data Index: 712865 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0595. Min Act: -0.0002

Data Index: 83997 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0599. Min Act: -0.0002

Data Index: 978239 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0612. Min Act: -0.0002

Data Index: 690891 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1331428 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1300986 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0564. Min Act: -0.0002

Data Index: 1303787 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1312187 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1115190 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0600. Min Act: -0.0002

Data Index: 309023 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 0.0734. Min Range: -0.0734

Max Act: 0.0616. Min Act: -0.0002

Data Index: 290439 (C4 (Web Text))

Max Activating Token Index: 868