Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 893 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0614. Min Act: -0.0004

Data Index: 399760 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0630. Min Act: -0.0004

Data Index: 565377 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0645. Min Act: -0.0004

Data Index: 993657 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0604. Min Act: -0.0004

Data Index: 1191404 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0625. Min Act: -0.0004

Data Index: 956032 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0573. Min Act: -0.0004

Data Index: 1022165 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0574. Min Act: -0.0004

Data Index: 165567 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0570. Min Act: -0.0004

Data Index: 658463 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0612. Min Act: -0.0004

Data Index: 344430 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0589. Min Act: -0.0004

Data Index: 855734 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0584. Min Act: -0.0004

Data Index: 1276161 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0563. Min Act: -0.0004

Data Index: 622959 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0583. Min Act: -0.0004

Data Index: 442923 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0541. Min Act: -0.0004

Data Index: 996057 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0564. Min Act: -0.0004

Data Index: 1314548 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0570. Min Act: -0.0004

Data Index: 396651 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0546. Min Act: -0.0004

Data Index: 513050 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0585. Min Act: -0.0004

Data Index: 945445 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0572. Min Act: -0.0004

Data Index: 69932 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.0645. Min Range: -0.0645

Max Act: 0.0555. Min Act: -0.0004

Data Index: 359671 (C4 (Web Text))

Max Activating Token Index: 396