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

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

Neuron 812 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: 0.0765. Min Range: -0.0765

Max Act: 0.0765. Min Act: -0.0003

Data Index: 75800 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0710. Min Act: -0.0002

Data Index: 286100 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0694. Min Act: -0.0003

Data Index: 247666 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0706. Min Act: -0.0002

Data Index: 358698 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0709. Min Act: -0.0002

Data Index: 242334 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0689. Min Act: -0.0001

Data Index: 1204827 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0645. Min Act: -0.0003

Data Index: 662556 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0630. Min Act: -0.0002

Data Index: 574312 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0644. Min Act: -0.0003

Data Index: 892810 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0617. Min Act: -0.0002

Data Index: 93906 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0624. Min Act: -0.0002

Data Index: 750439 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0607. Min Act: -0.0003

Data Index: 1037033 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0600. Min Act: -0.0003

Data Index: 542517 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0616. Min Act: -0.0003

Data Index: 1135235 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0599. Min Act: -0.0003

Data Index: 518626 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0621. Min Act: -0.0003

Data Index: 95183 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0603. Min Act: -0.0002

Data Index: 959195 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0603. Min Act: -0.0003

Data Index: 1320968 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0601. Min Act: -0.0000

Data Index: 877728 (C4 (Web Text))

Max Activating Token Index: 652

Text #19

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0590. Min Act: -0.0003

Data Index: 834841 (C4 (Web Text))

Max Activating Token Index: 5