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

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

Neuron 3051 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0662. Min Act: -0.0003

Data Index: 1335892 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1157694 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0646. Min Act: -0.0003

Data Index: 1341397 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0622. Min Act: -0.0002

Data Index: 93327 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1144414 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0590. Min Act: -0.0002

Data Index: 80787 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0586. Min Act: -0.0003

Data Index: 695451 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0568. Min Act: -0.0003

Data Index: 1287683 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0559. Min Act: -0.0002

Data Index: 295238 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0572. Min Act: -0.0003

Data Index: 937227 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0555. Min Act: -0.0002

Data Index: 710541 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1044665 (C4 (Web Text))

Max Activating Token Index: 194

Text #12

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0595. Min Act: -0.0003

Data Index: 59692 (C4 (Web Text))

Max Activating Token Index: 577

Text #13

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0554. Min Act: -0.0002

Data Index: 232285 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0546. Min Act: -0.0003

Data Index: 611594 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0581. Min Act: -0.0003

Data Index: 1093050 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0600. Min Act: -0.0002

Data Index: 977504 (C4 (Web Text))

Max Activating Token Index: 243

Text #17

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0529. Min Act: -0.0003

Data Index: 1106968 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0539. Min Act: -0.0003

Data Index: 749843 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0545. Min Act: -0.0003

Data Index: 148402 (C4 (Web Text))

Max Activating Token Index: 228