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

Dataset: The Pile

Neuron 702 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.3475. Min Act: -0.0000

Data Index: 862328 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.3315. Min Act: -0.0000

Data Index: 1751765 (The Pile)

Max Activating Token Index: 73

Text #2

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.3182. Min Act: -0.0000

Data Index: 290148 (The Pile)

Max Activating Token Index: 288

Text #3

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.3050. Min Act: -0.0000

Data Index: 1176776 (The Pile)

Max Activating Token Index: 440

Text #4

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1184783 (The Pile)

Max Activating Token Index: 598

Text #5

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.3025. Min Act: -0.0000

Data Index: 808932 (The Pile)

Max Activating Token Index: 441

Text #6

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.3008. Min Act: -0.0000

Data Index: 432839 (The Pile)

Max Activating Token Index: 267

Text #7

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2792. Min Act: -0.0000

Data Index: 1661575 (The Pile)

Max Activating Token Index: 394

Text #8

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2868. Min Act: -0.0000

Data Index: 475322 (The Pile)

Max Activating Token Index: 686

Text #9

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2855. Min Act: -0.0000

Data Index: 477513 (The Pile)

Max Activating Token Index: 20

Text #10

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2918. Min Act: -0.0000

Data Index: 484083 (The Pile)

Max Activating Token Index: 224

Text #11

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2806. Min Act: -0.0000

Data Index: 336185 (The Pile)

Max Activating Token Index: 872

Text #12

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2720. Min Act: -0.0000

Data Index: 1787487 (The Pile)

Max Activating Token Index: 80

Text #13

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1166096 (The Pile)

Max Activating Token Index: 479

Text #14

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2675. Min Act: -0.0000

Data Index: 274661 (The Pile)

Max Activating Token Index: 26

Text #15

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2607. Min Act: -0.0000

Data Index: 1034527 (The Pile)

Max Activating Token Index: 365

Text #16

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2766. Min Act: -0.0000

Data Index: 1081868 (The Pile)

Max Activating Token Index: 394

Text #17

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2773. Min Act: -0.0000

Data Index: 1453547 (The Pile)

Max Activating Token Index: 30

Text #18

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1728060 (The Pile)

Max Activating Token Index: 220

Text #19

Max Range: 0.3475. Min Range: -0.3475

Max Act: 0.2603. Min Act: -0.0000

Data Index: 733797 (The Pile)

Max Activating Token Index: 68