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

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

Neuron 582 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: 0.0753. Min Range: -0.0753

Max Act: 0.0753. Min Act: -0.0003

Data Index: 1514797 (Python Code)

Max Activating Token Index: 828

Text #1

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0663. Min Act: -0.0003

Data Index: 1439883 (Python Code)

Max Activating Token Index: 404

Text #2

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0647. Min Act: -0.0004

Data Index: 1430704 (Python Code)

Max Activating Token Index: 386

Text #3

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0646. Min Act: -0.0003

Data Index: 1582755 (Python Code)

Max Activating Token Index: 88

Text #4

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0687. Min Act: -0.0003

Data Index: 1605018 (Python Code)

Max Activating Token Index: 776

Text #5

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0610. Min Act: -0.0003

Data Index: 1494433 (Python Code)

Max Activating Token Index: 897

Text #6

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0615. Min Act: -0.0003

Data Index: 1033058 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0614. Min Act: -0.0003

Data Index: 1556992 (Python Code)

Max Activating Token Index: 894

Text #8

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0584. Min Act: -0.0003

Data Index: 1638410 (Python Code)

Max Activating Token Index: 174

Text #9

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0578. Min Act: -0.0003

Data Index: 1470609 (Python Code)

Max Activating Token Index: 835

Text #10

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0571. Min Act: -0.0004

Data Index: 677504 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1505544 (Python Code)

Max Activating Token Index: 893

Text #12

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1601825 (Python Code)

Max Activating Token Index: 221

Text #13

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1362775 (Python Code)

Max Activating Token Index: 962

Text #14

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0619. Min Act: -0.0003

Data Index: 1515906 (Python Code)

Max Activating Token Index: 861

Text #15

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0591. Min Act: -0.0002

Data Index: 1485174 (Python Code)

Max Activating Token Index: 972

Text #16

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0604. Min Act: -0.0003

Data Index: 1545703 (Python Code)

Max Activating Token Index: 368

Text #17

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1458688 (Python Code)

Max Activating Token Index: 353

Text #18

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0589. Min Act: -0.0003

Data Index: 1580756 (Python Code)

Max Activating Token Index: 62

Text #19

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0607. Min Act: -0.0003

Data Index: 1530144 (Python Code)

Max Activating Token Index: 874