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

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

Neuron 1158 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0757. Min Act: -0.0003

Data Index: 229747 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0809. Min Act: -0.0003

Data Index: 829617 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0697. Min Act: -0.0003

Data Index: 846866 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0716. Min Act: -0.0003

Data Index: 718078 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0689. Min Act: -0.0003

Data Index: 1187495 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0662. Min Act: -0.0003

Data Index: 999299 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0690. Min Act: -0.0003

Data Index: 78432 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0612. Min Act: -0.0003

Data Index: 889378 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0650. Min Act: -0.0003

Data Index: 891394 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0623. Min Act: -0.0003

Data Index: 1324947 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0622. Min Act: -0.0003

Data Index: 918519 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0600. Min Act: -0.0003

Data Index: 980447 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0568. Min Act: -0.0003

Data Index: 154436 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1216938 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0563. Min Act: -0.0003

Data Index: 1282738 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0576. Min Act: -0.0003

Data Index: 202860 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0550. Min Act: -0.0003

Data Index: 1278599 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0564. Min Act: -0.0003

Data Index: 378268 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0542. Min Act: -0.0003

Data Index: 813224 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.0809. Min Range: -0.0809

Max Act: 0.0551. Min Act: -0.0002

Data Index: 322638 (C4 (Web Text))

Max Activating Token Index: 380