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

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

Neuron 483 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1180. Min Act: -0.0002

Data Index: 404637 (C4 (Web Text))

Max Activating Token Index: 362

Text #1

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.1073. Min Act: -0.0002

Data Index: 262804 (C4 (Web Text))

Max Activating Token Index: 795

Text #2

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0920. Min Act: -0.0001

Data Index: 1309614 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0849. Min Act: -0.0002

Data Index: 455782 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0891. Min Act: -0.0002

Data Index: 1223847 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0883. Min Act: -0.0001

Data Index: 407504 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0857. Min Act: -0.0002

Data Index: 689167 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1199196 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0845. Min Act: -0.0002

Data Index: 715738 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0846. Min Act: -0.0002

Data Index: 909182 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0840. Min Act: -0.0002

Data Index: 715090 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0836. Min Act: -0.0001

Data Index: 843233 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0873. Min Act: -0.0002

Data Index: 332843 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0857. Min Act: -0.0002

Data Index: 107979 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0867. Min Act: -0.0002

Data Index: 312677 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0686. Min Act: -0.0002

Data Index: 986625 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0833. Min Act: -0.0002

Data Index: 32768 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0966. Min Act: -0.0001

Data Index: 588776 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0883. Min Act: -0.0001

Data Index: 1199495 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 0.1180. Min Range: -0.1180

Max Act: 0.0736. Min Act: -0.0002

Data Index: 663743 (C4 (Web Text))

Max Activating Token Index: 322