Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1896 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0745. Min Act: -0.0002

Data Index: 1420976 (Python Code)

Max Activating Token Index: 24

Text #1

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1451564 (Python Code)

Max Activating Token Index: 20

Text #2

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0721. Min Act: -0.0002

Data Index: 1539610 (Python Code)

Max Activating Token Index: 16

Text #3

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0715. Min Act: -0.0002

Data Index: 993055 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0676. Min Act: -0.0002

Data Index: 6454 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0719. Min Act: -0.0002

Data Index: 397481 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0711. Min Act: -0.0002

Data Index: 990748 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0706. Min Act: -0.0002

Data Index: 1244366 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0670. Min Act: -0.0002

Data Index: 655514 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0658. Min Act: -0.0002

Data Index: 1611975 (Python Code)

Max Activating Token Index: 784

Text #10

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1229480 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1395994 (Python Code)

Max Activating Token Index: 115

Text #12

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0680. Min Act: -0.0002

Data Index: 286304 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1549950 (Python Code)

Max Activating Token Index: 115

Text #14

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0654. Min Act: -0.0002

Data Index: 791634 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1501567 (Python Code)

Max Activating Token Index: 392

Text #16

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0667. Min Act: -0.0002

Data Index: 494091 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0645. Min Act: -0.0002

Data Index: 1408869 (Python Code)

Max Activating Token Index: 39

Text #18

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0651. Min Act: -0.0002

Data Index: 831153 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0635. Min Act: -0.0002

Data Index: 419819 (C4 (Web Text))

Max Activating Token Index: 545