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

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

Neuron 327 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8517. Min Range: -1.8517

Max Act: 1.8517. Min Act: -0.0000

Data Index: 493680 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 1.8517. Min Range: -1.8517

Max Act: 1.8409. Min Act: -0.0000

Data Index: 1048300 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 1.8517. Min Range: -1.8517

Max Act: 1.3145. Min Act: -0.0000

Data Index: 542493 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 1.8517. Min Range: -1.8517

Max Act: 1.2016. Min Act: -0.0000

Data Index: 766978 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 1.8517. Min Range: -1.8517

Max Act: 1.1310. Min Act: -0.0000

Data Index: 704566 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 1.8517. Min Range: -1.8517

Max Act: 1.2493. Min Act: 0.0000

Data Index: 1273508 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 1.8517. Min Range: -1.8517

Max Act: 1.3318. Min Act: 0.0000

Data Index: 143328 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 1.8517. Min Range: -1.8517

Max Act: 1.2289. Min Act: -0.0000

Data Index: 1237333 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 1.8517. Min Range: -1.8517

Max Act: 1.3270. Min Act: -0.0000

Data Index: 347190 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 1.8517. Min Range: -1.8517

Max Act: 1.2607. Min Act: -0.0000

Data Index: 792744 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 1.8517. Min Range: -1.8517

Max Act: 1.2372. Min Act: -0.0000

Data Index: 322895 (C4 (Web Text))

Max Activating Token Index: 773

Text #11

Max Range: 1.8517. Min Range: -1.8517

Max Act: 1.0968. Min Act: -0.0000

Data Index: 1510762 (Python Code)

Max Activating Token Index: 103

Text #12

Max Range: 1.8517. Min Range: -1.8517

Max Act: 1.1511. Min Act: 0.0000

Data Index: 1348085 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 1.8517. Min Range: -1.8517

Max Act: 1.0326. Min Act: -0.0000

Data Index: 665051 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 1.8517. Min Range: -1.8517

Max Act: 1.0361. Min Act: -0.0000

Data Index: 1631472 (Python Code)

Max Activating Token Index: 42

Text #15

Max Range: 1.8517. Min Range: -1.8517

Max Act: 1.0582. Min Act: 0.0000

Data Index: 1097487 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 1.8517. Min Range: -1.8517

Max Act: 1.0627. Min Act: -0.0000

Data Index: 1477171 (Python Code)

Max Activating Token Index: 1010

Text #17

Max Range: 1.8517. Min Range: -1.8517

Max Act: 1.0892. Min Act: -0.0000

Data Index: 527103 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 1.8517. Min Range: -1.8517

Max Act: 0.9318. Min Act: -0.0000

Data Index: 57961 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 1.8517. Min Range: -1.8517

Max Act: 1.0924. Min Act: -0.0000

Data Index: 1114099 (C4 (Web Text))

Max Activating Token Index: 580