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

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

Neuron 836 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: 0.0977. Min Range: -0.0977

Max Act: 0.0977. Min Act: -0.0005

Data Index: 908007 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0876. Min Act: -0.0005

Data Index: 1122096 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0908. Min Act: -0.0005

Data Index: 58595 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0798. Min Act: -0.0005

Data Index: 972232 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0848. Min Act: -0.0005

Data Index: 1219447 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0741. Min Act: -0.0005

Data Index: 957344 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0791. Min Act: -0.0005

Data Index: 829228 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0667. Min Act: -0.0005

Data Index: 64748 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0758. Min Act: -0.0005

Data Index: 37508 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0664. Min Act: -0.0005

Data Index: 15243 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0668. Min Act: -0.0005

Data Index: 628312 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0770. Min Act: -0.0005

Data Index: 1114943 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0744. Min Act: -0.0005

Data Index: 814104 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0703. Min Act: -0.0005

Data Index: 968148 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0670. Min Act: -0.0005

Data Index: 626323 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0689. Min Act: -0.0005

Data Index: 59502 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0704. Min Act: -0.0005

Data Index: 350840 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0676. Min Act: -0.0005

Data Index: 42376 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0711. Min Act: -0.0005

Data Index: 22552 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.0977. Min Range: -0.0977

Max Act: 0.0667. Min Act: -0.0005

Data Index: 739805 (C4 (Web Text))

Max Activating Token Index: 468