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

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

Neuron 3370 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.2332. Min Act: -0.0000

Data Index: 600996 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.2114. Min Act: -0.0000

Data Index: 724709 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.2026. Min Act: -0.0001

Data Index: 1336318 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.2076. Min Act: -0.0000

Data Index: 84045 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1838. Min Act: -0.0001

Data Index: 706634 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1858. Min Act: -0.0001

Data Index: 1301989 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1817. Min Act: -0.0000

Data Index: 493844 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1952. Min Act: -0.0000

Data Index: 1323760 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1927. Min Act: -0.0000

Data Index: 24891 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1703. Min Act: -0.0000

Data Index: 299786 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1866. Min Act: -0.0000

Data Index: 662214 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1783. Min Act: -0.0000

Data Index: 749414 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1808. Min Act: -0.0000

Data Index: 1214030 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1844. Min Act: -0.0000

Data Index: 366014 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1764. Min Act: -0.0000

Data Index: 727529 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1693. Min Act: -0.0000

Data Index: 184888 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1623. Min Act: -0.0001

Data Index: 586016 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1678. Min Act: -0.0000

Data Index: 1144649 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1686. Min Act: -0.0000

Data Index: 117794 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 0.2332. Min Range: -0.2332

Max Act: 0.1669. Min Act: -0.0000

Data Index: 888966 (C4 (Web Text))

Max Activating Token Index: 139