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

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

Neuron 1002 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: 2.4859. Min Range: -2.4859

Max Act: 2.4859. Min Act: -0.0000

Data Index: 953392 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 2.4859. Min Range: -2.4859

Max Act: 1.9488. Min Act: -0.0000

Data Index: 542743 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 2.4859. Min Range: -2.4859

Max Act: 1.7189. Min Act: -0.0000

Data Index: 366993 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 2.4859. Min Range: -2.4859

Max Act: 1.6538. Min Act: -0.0000

Data Index: 213897 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 2.4859. Min Range: -2.4859

Max Act: 1.5703. Min Act: -0.0000

Data Index: 125000 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 2.4859. Min Range: -2.4859

Max Act: 1.4558. Min Act: -0.0000

Data Index: 351406 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 2.4859. Min Range: -2.4859

Max Act: 1.5594. Min Act: 0.0000

Data Index: 96779 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 2.4859. Min Range: -2.4859

Max Act: 1.3920. Min Act: -0.0000

Data Index: 463106 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 2.4859. Min Range: -2.4859

Max Act: 1.3127. Min Act: -0.0000

Data Index: 1358995 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 2.4859. Min Range: -2.4859

Max Act: 1.3890. Min Act: -0.0000

Data Index: 1336992 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 2.4859. Min Range: -2.4859

Max Act: 1.2172. Min Act: -0.0000

Data Index: 893803 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 2.4859. Min Range: -2.4859

Max Act: 1.2909. Min Act: -0.0000

Data Index: 761648 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 2.4859. Min Range: -2.4859

Max Act: 1.2884. Min Act: -0.0000

Data Index: 628934 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 2.4859. Min Range: -2.4859

Max Act: 1.2886. Min Act: -0.0000

Data Index: 765777 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 2.4859. Min Range: -2.4859

Max Act: 1.2614. Min Act: -0.0000

Data Index: 332674 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 2.4859. Min Range: -2.4859

Max Act: 1.2176. Min Act: -0.0000

Data Index: 296879 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 2.4859. Min Range: -2.4859

Max Act: 1.2131. Min Act: -0.0000

Data Index: 835806 (C4 (Web Text))

Max Activating Token Index: 447

Text #17

Max Range: 2.4859. Min Range: -2.4859

Max Act: 1.2783. Min Act: -0.0000

Data Index: 87307 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 2.4859. Min Range: -2.4859

Max Act: 1.2010. Min Act: -0.0000

Data Index: 746702 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 2.4859. Min Range: -2.4859

Max Act: 1.2022. Min Act: -0.0000

Data Index: 796213 (C4 (Web Text))

Max Activating Token Index: 882