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

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

Neuron 3565 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.9226. Min Act: -0.0000

Data Index: 420373 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.8619. Min Act: -0.0000

Data Index: 108838 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.4889. Min Act: -0.0000

Data Index: 167864 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.6232. Min Act: -0.0000

Data Index: 84883 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.7668. Min Act: -0.0000

Data Index: 582626 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.5539. Min Act: -0.0000

Data Index: 331938 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.5379. Min Act: -0.0000

Data Index: 677196 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.1685. Min Act: -0.0000

Data Index: 325415 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.5434. Min Act: -0.0000

Data Index: 1341982 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.2242. Min Act: -0.0000

Data Index: 871852 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.2479. Min Act: -0.0000

Data Index: 1358380 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.4173. Min Act: -0.0000

Data Index: 65908 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.2854. Min Act: -0.0000

Data Index: 655672 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.3821. Min Act: -0.0000

Data Index: 1390835 (Python Code)

Max Activating Token Index: 49

Text #14

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.3328. Min Act: -0.0000

Data Index: 1395624 (Python Code)

Max Activating Token Index: 247

Text #15

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.3454. Min Act: -0.0000

Data Index: 1169671 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.2035. Min Act: -0.0000

Data Index: 1369989 (Python Code)

Max Activating Token Index: 70

Text #17

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.2014. Min Act: -0.0000

Data Index: 136485 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.0920. Min Act: -0.0000

Data Index: 206035 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 2.9226. Min Range: -2.9226

Max Act: 2.1553. Min Act: -0.0000

Data Index: 768105 (C4 (Web Text))

Max Activating Token Index: 734