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

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

Neuron 3243 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5906. Min Range: -2.5906

Max Act: 2.5669. Min Act: -0.0000

Data Index: 140872 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 2.5906. Min Range: -2.5906

Max Act: 2.5906. Min Act: -0.0000

Data Index: 355543 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 2.5906. Min Range: -2.5906

Max Act: 2.5589. Min Act: -0.0000

Data Index: 284221 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 2.5906. Min Range: -2.5906

Max Act: 2.5052. Min Act: -0.0000

Data Index: 923777 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 2.5906. Min Range: -2.5906

Max Act: 2.4791. Min Act: -0.0000

Data Index: 1347723 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 2.5906. Min Range: -2.5906

Max Act: 2.3055. Min Act: -0.0000

Data Index: 1308776 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 2.5906. Min Range: -2.5906

Max Act: 2.3981. Min Act: -0.0000

Data Index: 155535 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 2.5906. Min Range: -2.5906

Max Act: 2.4377. Min Act: -0.0000

Data Index: 839470 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 2.5906. Min Range: -2.5906

Max Act: 2.4746. Min Act: -0.0000

Data Index: 475571 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 2.5906. Min Range: -2.5906

Max Act: 2.4426. Min Act: -0.0000

Data Index: 956475 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 2.5906. Min Range: -2.5906

Max Act: 2.4188. Min Act: -0.0000

Data Index: 945172 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 2.5906. Min Range: -2.5906

Max Act: 2.4256. Min Act: -0.0000

Data Index: 180818 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 2.5906. Min Range: -2.5906

Max Act: 2.4084. Min Act: -0.0000

Data Index: 416868 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 2.5906. Min Range: -2.5906

Max Act: 2.3503. Min Act: -0.0000

Data Index: 1274154 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 2.5906. Min Range: -2.5906

Max Act: 2.5819. Min Act: -0.0000

Data Index: 796521 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 2.5906. Min Range: -2.5906

Max Act: 2.4600. Min Act: -0.0000

Data Index: 857986 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 2.5906. Min Range: -2.5906

Max Act: 2.3899. Min Act: -0.0000

Data Index: 613175 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 2.5906. Min Range: -2.5906

Max Act: 2.3306. Min Act: -0.0000

Data Index: 1112071 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 2.5906. Min Range: -2.5906

Max Act: 2.3123. Min Act: -0.0000

Data Index: 988457 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 2.5906. Min Range: -2.5906

Max Act: 2.3007. Min Act: -0.0000

Data Index: 1104353 (C4 (Web Text))

Max Activating Token Index: 423