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

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

Neuron 1479 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0761. Min Act: -0.0006

Data Index: 547641 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0730. Min Act: -0.0006

Data Index: 303258 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0681. Min Act: -0.0006

Data Index: 735653 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0677. Min Act: -0.0006

Data Index: 1138612 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0720. Min Act: -0.0006

Data Index: 844452 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0605. Min Act: -0.0006

Data Index: 544552 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0655. Min Act: -0.0006

Data Index: 912474 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0652. Min Act: -0.0006

Data Index: 287782 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0650. Min Act: -0.0006

Data Index: 891383 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0621. Min Act: -0.0006

Data Index: 567679 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0667. Min Act: -0.0006

Data Index: 752850 (C4 (Web Text))

Max Activating Token Index: 847

Text #11

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0688. Min Act: -0.0006

Data Index: 728563 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0612. Min Act: -0.0006

Data Index: 490128 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0609. Min Act: -0.0006

Data Index: 122592 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0636. Min Act: -0.0006

Data Index: 1085884 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0633. Min Act: -0.0006

Data Index: 969505 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0631. Min Act: -0.0006

Data Index: 436413 (C4 (Web Text))

Max Activating Token Index: 35

Text #17

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0600. Min Act: -0.0006

Data Index: 320235 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0623. Min Act: -0.0006

Data Index: 143977 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0619. Min Act: -0.0006

Data Index: 1120790 (C4 (Web Text))

Max Activating Token Index: 529