Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3733 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.3565. Min Act: -0.0000

Data Index: 1149067 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.3868. Min Act: -0.0000

Data Index: 247847 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.3308. Min Act: -0.0000

Data Index: 1219152 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.3134. Min Act: -0.0000

Data Index: 311199 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.2877. Min Act: -0.0000

Data Index: 189473 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.2771. Min Act: -0.0000

Data Index: 1038401 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.2442. Min Act: -0.0000

Data Index: 683520 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.2132. Min Act: -0.0000

Data Index: 107992 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.1961. Min Act: -0.0000

Data Index: 564581 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.2262. Min Act: -0.0000

Data Index: 438401 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.1933. Min Act: -0.0000

Data Index: 680368 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.1853. Min Act: -0.0000

Data Index: 161048 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.1772. Min Act: -0.0000

Data Index: 975699 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.1830. Min Act: -0.0000

Data Index: 921371 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.1896. Min Act: -0.0000

Data Index: 435367 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.1844. Min Act: -0.0000

Data Index: 160114 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.1648. Min Act: -0.0000

Data Index: 589661 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.2043. Min Act: -0.0000

Data Index: 204650 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.1669. Min Act: -0.0000

Data Index: 964483 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.3868. Min Range: -0.3868

Max Act: 0.1546. Min Act: -0.0000

Data Index: 500762 (C4 (Web Text))

Max Activating Token Index: 668