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

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

Neuron 1478 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: 0.0694. Min Range: -0.0694

Max Act: 0.0694. Min Act: -0.0003

Data Index: 870979 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0609. Min Act: -0.0003

Data Index: 1250849 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0601. Min Act: -0.0003

Data Index: 553162 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0589. Min Act: -0.0004

Data Index: 95332 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0564. Min Act: -0.0003

Data Index: 577402 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0577. Min Act: -0.0002

Data Index: 786953 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0561. Min Act: -0.0003

Data Index: 933844 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0549. Min Act: -0.0003

Data Index: 829737 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0547. Min Act: -0.0003

Data Index: 868073 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0556. Min Act: -0.0003

Data Index: 1335951 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0539. Min Act: -0.0003

Data Index: 1114101 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0540. Min Act: -0.0003

Data Index: 136478 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0542. Min Act: -0.0003

Data Index: 917478 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0538. Min Act: -0.0004

Data Index: 791490 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1126173 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0536. Min Act: -0.0003

Data Index: 730969 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0528. Min Act: -0.0003

Data Index: 670411 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0536. Min Act: -0.0003

Data Index: 774559 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0493. Min Act: -0.0003

Data Index: 458597 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.0694. Min Range: -0.0694

Max Act: 0.0520. Min Act: -0.0003

Data Index: 1043355 (C4 (Web Text))

Max Activating Token Index: 708