Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3846 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0782. Min Act: -0.0001

Data Index: 738121 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0830. Min Act: -0.0001

Data Index: 340538 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0639. Min Act: -0.0001

Data Index: 567799 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0708. Min Act: -0.0001

Data Index: 188686 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0724. Min Act: -0.0001

Data Index: 395163 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1346924 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0751. Min Act: -0.0001

Data Index: 597929 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0688. Min Act: -0.0001

Data Index: 929806 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0638. Min Act: -0.0001

Data Index: 173671 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0701. Min Act: -0.0001

Data Index: 1039922 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0686. Min Act: -0.0001

Data Index: 1089267 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1253395 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0629. Min Act: -0.0001

Data Index: 30206 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1181285 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0641. Min Act: -0.0001

Data Index: 971028 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0668. Min Act: -0.0001

Data Index: 1032681 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1062273 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0697. Min Act: -0.0001

Data Index: 466353 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0690. Min Act: -0.0001

Data Index: 1147724 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.0830. Min Range: -0.0830

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1069393 (C4 (Web Text))

Max Activating Token Index: 24