Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 847 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0684. Min Act: -0.0004

Data Index: 1100615 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0672. Min Act: -0.0003

Data Index: 382399 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0656. Min Act: -0.0003

Data Index: 153113 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0607. Min Act: -0.0003

Data Index: 1054107 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0600. Min Act: -0.0003

Data Index: 638545 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0570. Min Act: -0.0002

Data Index: 225596 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0576. Min Act: -0.0004

Data Index: 599178 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0548. Min Act: -0.0003

Data Index: 421431 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0551. Min Act: -0.0003

Data Index: 93497 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0554. Min Act: -0.0002

Data Index: 900329 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0489. Min Act: -0.0003

Data Index: 250848 (C4 (Web Text))

Max Activating Token Index: 399

Text #11

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0513. Min Act: -0.0002

Data Index: 17823 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0533. Min Act: -0.0003

Data Index: 465870 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0531. Min Act: -0.0003

Data Index: 629510 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0497. Min Act: -0.0002

Data Index: 46665 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0538. Min Act: -0.0003

Data Index: 223367 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0555. Min Act: -0.0003

Data Index: 984324 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0476. Min Act: -0.0003

Data Index: 1340326 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0473. Min Act: -0.0003

Data Index: 1251963 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0498. Min Act: -0.0003

Data Index: 786135 (C4 (Web Text))

Max Activating Token Index: 374