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

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

Neuron 319 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0627. Min Act: -0.0002

Data Index: 901914 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0629. Min Act: -0.0002

Data Index: 1099684 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0459. Min Act: -0.0002

Data Index: 631043 (C4 (Web Text))

Max Activating Token Index: 124

Text #3

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1156818 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0520. Min Act: -0.0002

Data Index: 857695 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0510. Min Act: -0.0002

Data Index: 950554 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0500. Min Act: -0.0002

Data Index: 981427 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1158868 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0498. Min Act: -0.0002

Data Index: 894116 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0451. Min Act: -0.0002

Data Index: 1093923 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0450. Min Act: -0.0002

Data Index: 200901 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0458. Min Act: -0.0002

Data Index: 751066 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0432. Min Act: -0.0002

Data Index: 919423 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0412. Min Act: -0.0002

Data Index: 818923 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0474. Min Act: -0.0002

Data Index: 943615 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1024666 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0427. Min Act: -0.0002

Data Index: 489185 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0400. Min Act: -0.0002

Data Index: 345886 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0426. Min Act: -0.0002

Data Index: 960167 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.0629. Min Range: -0.0629

Max Act: 0.0419. Min Act: -0.0002

Data Index: 553070 (C4 (Web Text))

Max Activating Token Index: 213