Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 343 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0738. Min Act: -0.0002

Data Index: 19717 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0629. Min Act: -0.0002

Data Index: 354522 (C4 (Web Text))

Max Activating Token Index: 532

Text #2

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0603. Min Act: -0.0002

Data Index: 997541 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0636. Min Act: -0.0002

Data Index: 419562 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0617. Min Act: -0.0002

Data Index: 349162 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0623. Min Act: -0.0002

Data Index: 780194 (C4 (Web Text))

Max Activating Token Index: 856

Text #6

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0608. Min Act: -0.0002

Data Index: 874169 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0601. Min Act: -0.0002

Data Index: 838986 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0587. Min Act: -0.0002

Data Index: 361234 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0580. Min Act: -0.0002

Data Index: 763377 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0600. Min Act: -0.0002

Data Index: 332240 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0597. Min Act: -0.0002

Data Index: 357105 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0584. Min Act: -0.0002

Data Index: 93061 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1036353 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0568. Min Act: -0.0002

Data Index: 819536 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0606. Min Act: -0.0002

Data Index: 875268 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0586. Min Act: -0.0002

Data Index: 446743 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0570. Min Act: -0.0002

Data Index: 229360 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0580. Min Act: -0.0002

Data Index: 322687 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0569. Min Act: -0.0002

Data Index: 267001 (C4 (Web Text))

Max Activating Token Index: 946