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

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

Neuron 1643 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0762. Min Act: -0.0001

Data Index: 528109 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0764. Min Act: -0.0001

Data Index: 202187 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0704. Min Act: -0.0001

Data Index: 348542 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0754. Min Act: -0.0001

Data Index: 1526932 (Python Code)

Max Activating Token Index: 147

Text #4

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0699. Min Act: -0.0001

Data Index: 25337 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1048770 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0679. Min Act: -0.0001

Data Index: 920315 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1301474 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0640. Min Act: -0.0000

Data Index: 596338 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0587. Min Act: -0.0000

Data Index: 832517 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0630. Min Act: -0.0001

Data Index: 681903 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0615. Min Act: -0.0001

Data Index: 825203 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0619. Min Act: -0.0001

Data Index: 1285242 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0577. Min Act: -0.0001

Data Index: 1349417 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0586. Min Act: -0.0001

Data Index: 1341131 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0551. Min Act: -0.0000

Data Index: 1115756 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0587. Min Act: -0.0001

Data Index: 716170 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0598. Min Act: -0.0001

Data Index: 179131 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0558. Min Act: -0.0001

Data Index: 1166990 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 0.0764. Min Range: -0.0764

Max Act: 0.0551. Min Act: -0.0001

Data Index: 91448 (C4 (Web Text))

Max Activating Token Index: 178