Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3357 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.9857. Min Range: -2.9857

Max Act: 2.9857. Min Act: -0.0001

Data Index: 950535 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 2.9857. Min Range: -2.9857

Max Act: 2.9637. Min Act: -0.0000

Data Index: 234302 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 2.9857. Min Range: -2.9857

Max Act: 2.9681. Min Act: -0.0000

Data Index: 47781 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 2.9857. Min Range: -2.9857

Max Act: 2.8175. Min Act: -0.0000

Data Index: 372656 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 2.9857. Min Range: -2.9857

Max Act: 2.6589. Min Act: -0.0000

Data Index: 225426 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 2.9857. Min Range: -2.9857

Max Act: 2.5269. Min Act: -0.0000

Data Index: 1316065 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 2.9857. Min Range: -2.9857

Max Act: 2.3217. Min Act: -0.0000

Data Index: 391711 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 2.9857. Min Range: -2.9857

Max Act: 2.2839. Min Act: -0.0000

Data Index: 209828 (C4 (Web Text))

Max Activating Token Index: 527

Text #8

Max Range: 2.9857. Min Range: -2.9857

Max Act: 2.2230. Min Act: -0.0000

Data Index: 717873 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 2.9857. Min Range: -2.9857

Max Act: 2.2065. Min Act: -0.0000

Data Index: 335645 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 2.9857. Min Range: -2.9857

Max Act: 2.1984. Min Act: -0.0000

Data Index: 525955 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 2.9857. Min Range: -2.9857

Max Act: 2.2683. Min Act: -0.0000

Data Index: 350757 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 2.9857. Min Range: -2.9857

Max Act: 2.1087. Min Act: -0.0000

Data Index: 1178040 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 2.9857. Min Range: -2.9857

Max Act: 1.9376. Min Act: -0.0000

Data Index: 999267 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 2.9857. Min Range: -2.9857

Max Act: 1.9400. Min Act: -0.0000

Data Index: 460740 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 2.9857. Min Range: -2.9857

Max Act: 1.8135. Min Act: -0.0000

Data Index: 1253928 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 2.9857. Min Range: -2.9857

Max Act: 1.8718. Min Act: -0.0000

Data Index: 414970 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 2.9857. Min Range: -2.9857

Max Act: 1.8307. Min Act: -0.0000

Data Index: 446774 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 2.9857. Min Range: -2.9857

Max Act: 1.8119. Min Act: -0.0000

Data Index: 863467 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 2.9857. Min Range: -2.9857

Max Act: 1.6255. Min Act: -0.0000

Data Index: 930235 (C4 (Web Text))

Max Activating Token Index: 691