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

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

Neuron 4559 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0701. Min Range: -2.0701

Max Act: 2.0701. Min Act: -0.0000

Data Index: 16008 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 2.0701. Min Range: -2.0701

Max Act: 1.8112. Min Act: -0.0000

Data Index: 352898 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 2.0701. Min Range: -2.0701

Max Act: 1.7853. Min Act: -0.0000

Data Index: 4535 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 2.0701. Min Range: -2.0701

Max Act: 1.6843. Min Act: -0.0000

Data Index: 1046163 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 2.0701. Min Range: -2.0701

Max Act: 1.5706. Min Act: -0.0000

Data Index: 346626 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 2.0701. Min Range: -2.0701

Max Act: 1.6505. Min Act: -0.0000

Data Index: 653704 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 2.0701. Min Range: -2.0701

Max Act: 1.4834. Min Act: -0.0000

Data Index: 970748 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 2.0701. Min Range: -2.0701

Max Act: 1.5642. Min Act: -0.0000

Data Index: 30230 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 2.0701. Min Range: -2.0701

Max Act: 1.4579. Min Act: -0.0000

Data Index: 1187882 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 2.0701. Min Range: -2.0701

Max Act: 1.5437. Min Act: -0.0000

Data Index: 127129 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 2.0701. Min Range: -2.0701

Max Act: 1.4465. Min Act: -0.0000

Data Index: 273567 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 2.0701. Min Range: -2.0701

Max Act: 1.4446. Min Act: -0.0000

Data Index: 1032817 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 2.0701. Min Range: -2.0701

Max Act: 1.5097. Min Act: -0.0000

Data Index: 536972 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 2.0701. Min Range: -2.0701

Max Act: 1.4844. Min Act: -0.0000

Data Index: 863807 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 2.0701. Min Range: -2.0701

Max Act: 1.3802. Min Act: -0.0000

Data Index: 649304 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 2.0701. Min Range: -2.0701

Max Act: 1.3679. Min Act: -0.0000

Data Index: 520343 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 2.0701. Min Range: -2.0701

Max Act: 1.4353. Min Act: -0.0000

Data Index: 1066909 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 2.0701. Min Range: -2.0701

Max Act: 1.4256. Min Act: -0.0000

Data Index: 1120492 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 2.0701. Min Range: -2.0701

Max Act: 1.3429. Min Act: -0.0000

Data Index: 1075114 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 2.0701. Min Range: -2.0701

Max Act: 1.4090. Min Act: -0.0000

Data Index: 1237452 (C4 (Web Text))

Max Activating Token Index: 695