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

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

Neuron 3755 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: 0.0928. Min Range: -0.0928

Max Act: 0.0928. Min Act: -0.0002

Data Index: 873253 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0884. Min Act: -0.0002

Data Index: 163901 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1031765 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1075959 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0728. Min Act: -0.0002

Data Index: 805942 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0714. Min Act: -0.0002

Data Index: 910391 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0674. Min Act: -0.0002

Data Index: 36896 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0731. Min Act: -0.0002

Data Index: 255116 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0781. Min Act: -0.0002

Data Index: 996764 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0685. Min Act: -0.0002

Data Index: 967432 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1296221 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0910. Min Act: -0.0002

Data Index: 531918 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0842. Min Act: -0.0002

Data Index: 350740 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0759. Min Act: -0.0002

Data Index: 1189945 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0657. Min Act: -0.0002

Data Index: 476327 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0582. Min Act: -0.0002

Data Index: 731166 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0669. Min Act: -0.0002

Data Index: 543521 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0737. Min Act: -0.0002

Data Index: 1019035 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0608. Min Act: -0.0002

Data Index: 968649 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0565. Min Act: -0.0002

Data Index: 518593 (C4 (Web Text))

Max Activating Token Index: 607