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

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

Neuron 2921 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9722. Min Range: -2.9722

Max Act: 2.9722. Min Act: -0.0000

Data Index: 658647 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 2.9722. Min Range: -2.9722

Max Act: 2.4366. Min Act: -0.0000

Data Index: 670105 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 2.9722. Min Range: -2.9722

Max Act: 2.1621. Min Act: 0.0000

Data Index: 328897 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 2.9722. Min Range: -2.9722

Max Act: 1.9162. Min Act: -0.0000

Data Index: 417493 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 2.9722. Min Range: -2.9722

Max Act: 1.8019. Min Act: -0.0000

Data Index: 1307442 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 2.9722. Min Range: -2.9722

Max Act: 1.7716. Min Act: -0.0000

Data Index: 551809 (C4 (Web Text))

Max Activating Token Index: 715

Text #6

Max Range: 2.9722. Min Range: -2.9722

Max Act: 1.8563. Min Act: -0.0000

Data Index: 1288090 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 2.9722. Min Range: -2.9722

Max Act: 1.7492. Min Act: -0.0000

Data Index: 341207 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 2.9722. Min Range: -2.9722

Max Act: 1.8169. Min Act: -0.0000

Data Index: 667352 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 2.9722. Min Range: -2.9722

Max Act: 1.4902. Min Act: -0.0000

Data Index: 519158 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 2.9722. Min Range: -2.9722

Max Act: 1.5816. Min Act: -0.0000

Data Index: 211732 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 2.9722. Min Range: -2.9722

Max Act: 1.6135. Min Act: -0.0000

Data Index: 1284348 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 2.9722. Min Range: -2.9722

Max Act: 1.6086. Min Act: -0.0000

Data Index: 895894 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 2.9722. Min Range: -2.9722

Max Act: 1.5144. Min Act: -0.0000

Data Index: 76834 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 2.9722. Min Range: -2.9722

Max Act: 1.5029. Min Act: -0.0000

Data Index: 525930 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 2.9722. Min Range: -2.9722

Max Act: 1.5599. Min Act: -0.0000

Data Index: 661562 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 2.9722. Min Range: -2.9722

Max Act: 1.4615. Min Act: -0.0000

Data Index: 1222764 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 2.9722. Min Range: -2.9722

Max Act: 1.4155. Min Act: -0.0000

Data Index: 371488 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 2.9722. Min Range: -2.9722

Max Act: 1.3170. Min Act: -0.0000

Data Index: 1245353 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 2.9722. Min Range: -2.9722

Max Act: 1.3915. Min Act: -0.0000

Data Index: 627107 (C4 (Web Text))

Max Activating Token Index: 462