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

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

Neuron 435 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0747. Min Act: -0.0005

Data Index: 669707 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0723. Min Act: -0.0005

Data Index: 1000285 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0651. Min Act: -0.0005

Data Index: 1250766 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0626. Min Act: -0.0005

Data Index: 209077 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0646. Min Act: -0.0005

Data Index: 807178 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0654. Min Act: -0.0005

Data Index: 28179 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0615. Min Act: -0.0005

Data Index: 410667 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0665. Min Act: -0.0005

Data Index: 556686 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0628. Min Act: -0.0005

Data Index: 1321004 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0614. Min Act: -0.0005

Data Index: 476622 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0634. Min Act: -0.0005

Data Index: 1261646 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0575. Min Act: -0.0005

Data Index: 464538 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0621. Min Act: -0.0005

Data Index: 1164989 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0643. Min Act: -0.0005

Data Index: 544048 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0609. Min Act: -0.0005

Data Index: 23703 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0598. Min Act: -0.0005

Data Index: 1038611 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0603. Min Act: -0.0005

Data Index: 713393 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0584. Min Act: -0.0005

Data Index: 471135 (C4 (Web Text))

Max Activating Token Index: 538

Text #18

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0619. Min Act: -0.0005

Data Index: 664553 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0581. Min Act: -0.0005

Data Index: 834458 (C4 (Web Text))

Max Activating Token Index: 729