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

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

Neuron 1737 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.7857. Min Act: -0.0000

Data Index: 791480 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.7597. Min Act: -0.0000

Data Index: 354832 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.7226. Min Act: -0.0000

Data Index: 1195927 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6947. Min Act: -0.0000

Data Index: 578936 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6681. Min Act: -0.0000

Data Index: 1059712 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6395. Min Act: -0.0000

Data Index: 535686 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6461. Min Act: -0.0000

Data Index: 57080 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6390. Min Act: -0.0000

Data Index: 484567 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6292. Min Act: -0.0000

Data Index: 684989 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6404. Min Act: -0.0000

Data Index: 1246668 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6748. Min Act: -0.0000

Data Index: 693711 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5895. Min Act: -0.0000

Data Index: 186911 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5816. Min Act: -0.0000

Data Index: 842501 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.6193. Min Act: -0.0000

Data Index: 371373 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1167038 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5594. Min Act: -0.0000

Data Index: 642297 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5979. Min Act: -0.0000

Data Index: 1196775 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1060409 (C4 (Web Text))

Max Activating Token Index: 644

Text #18

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5703. Min Act: -0.0000

Data Index: 906482 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 0.7857. Min Range: -0.7857

Max Act: 0.5527. Min Act: -0.0000

Data Index: 1144604 (C4 (Web Text))

Max Activating Token Index: 616