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

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

Neuron 5971 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1693. Min Act: -0.0002

Data Index: 866039 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1392. Min Act: -0.0002

Data Index: 961879 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1320. Min Act: -0.0002

Data Index: 197088 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1307. Min Act: -0.0002

Data Index: 488291 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1208. Min Act: -0.0002

Data Index: 1328031 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1221. Min Act: -0.0002

Data Index: 197016 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1180. Min Act: -0.0002

Data Index: 885039 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1129. Min Act: -0.0002

Data Index: 1226557 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1127. Min Act: -0.0002

Data Index: 973624 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1105. Min Act: -0.0002

Data Index: 906505 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.0982. Min Act: -0.0002

Data Index: 55271 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.1001. Min Act: -0.0002

Data Index: 838897 (C4 (Web Text))

Max Activating Token Index: 371

Text #12

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.0967. Min Act: -0.0002

Data Index: 879757 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.0957. Min Act: -0.0002

Data Index: 690600 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.0923. Min Act: -0.0002

Data Index: 1346065 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.0919. Min Act: -0.0002

Data Index: 516561 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.0911. Min Act: -0.0002

Data Index: 394464 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.0909. Min Act: -0.0002

Data Index: 858948 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.0940. Min Act: -0.0002

Data Index: 40190 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 0.1693. Min Range: -0.1693

Max Act: 0.0868. Min Act: -0.0002

Data Index: 590741 (C4 (Web Text))

Max Activating Token Index: 753