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

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

Neuron 244 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: 0.0971. Min Range: -0.0971

Max Act: 0.0969. Min Act: -0.0003

Data Index: 609735 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0971. Min Act: -0.0002

Data Index: 662827 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0826. Min Act: -0.0002

Data Index: 239859 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0857. Min Act: -0.0003

Data Index: 568311 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0769. Min Act: -0.0003

Data Index: 1261480 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0806. Min Act: -0.0003

Data Index: 1072129 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0784. Min Act: -0.0002

Data Index: 401650 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0791. Min Act: -0.0003

Data Index: 648121 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0781. Min Act: -0.0003

Data Index: 1120700 (C4 (Web Text))

Max Activating Token Index: 179

Text #9

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0749. Min Act: -0.0002

Data Index: 1047368 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0760. Min Act: -0.0002

Data Index: 560981 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0801. Min Act: -0.0003

Data Index: 397672 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0759. Min Act: -0.0002

Data Index: 215346 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0730. Min Act: -0.0002

Data Index: 511509 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0723. Min Act: -0.0003

Data Index: 684918 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0750. Min Act: -0.0003

Data Index: 161587 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0737. Min Act: -0.0002

Data Index: 904046 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0725. Min Act: -0.0003

Data Index: 1067041 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0746. Min Act: -0.0002

Data Index: 747487 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0702. Min Act: -0.0002

Data Index: 497179 (C4 (Web Text))

Max Activating Token Index: 714