Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5000 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0758. Min Act: -0.0002

Data Index: 346525 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0719. Min Act: -0.0002

Data Index: 146812 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0676. Min Act: -0.0002

Data Index: 514859 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0685. Min Act: -0.0002

Data Index: 259871 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0656. Min Act: -0.0002

Data Index: 951428 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0650. Min Act: -0.0002

Data Index: 324657 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0635. Min Act: -0.0002

Data Index: 794810 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1194395 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0563. Min Act: -0.0002

Data Index: 133483 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0578. Min Act: -0.0002

Data Index: 143195 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0555. Min Act: -0.0002

Data Index: 89613 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0568. Min Act: -0.0002

Data Index: 152135 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0566. Min Act: -0.0002

Data Index: 912220 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0556. Min Act: -0.0002

Data Index: 250814 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0552. Min Act: -0.0002

Data Index: 247355 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1358089 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0526. Min Act: -0.0002

Data Index: 354636 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0544. Min Act: -0.0002

Data Index: 649660 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0545. Min Act: -0.0002

Data Index: 784257 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.0758. Min Range: -0.0758

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1267637 (C4 (Web Text))

Max Activating Token Index: 389