Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 647 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1725. Min Range: -1.1725

Max Act: 1.1725. Min Act: -0.0001

Data Index: 1248397 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 1.1725. Min Range: -1.1725

Max Act: 1.0707. Min Act: -0.0001

Data Index: 726559 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 1.1725. Min Range: -1.1725

Max Act: 1.0147. Min Act: -0.0001

Data Index: 961378 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 1.1725. Min Range: -1.1725

Max Act: 1.0492. Min Act: -0.0001

Data Index: 1032511 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.7931. Min Act: -0.0001

Data Index: 1000222 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.9079. Min Act: -0.0001

Data Index: 610651 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.8732. Min Act: -0.0001

Data Index: 23796 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.8374. Min Act: -0.0001

Data Index: 393256 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.8544. Min Act: -0.0001

Data Index: 520386 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.8747. Min Act: -0.0001

Data Index: 60833 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.8105. Min Act: -0.0001

Data Index: 1214972 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.8168. Min Act: -0.0001

Data Index: 195394 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.7796. Min Act: -0.0001

Data Index: 621532 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.8033. Min Act: -0.0001

Data Index: 684132 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.8255. Min Act: -0.0001

Data Index: 1152982 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.7792. Min Act: -0.0001

Data Index: 1241037 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.6829. Min Act: -0.0001

Data Index: 1350973 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.7186. Min Act: -0.0001

Data Index: 289631 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.7573. Min Act: -0.0001

Data Index: 172973 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 1.1725. Min Range: -1.1725

Max Act: 0.7544. Min Act: -0.0001

Data Index: 810595 (C4 (Web Text))

Max Activating Token Index: 788