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

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

Neuron 3292 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: 1.5427. Min Range: -1.5427

Max Act: 1.5414. Min Act: -0.0000

Data Index: 1167762 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.4624. Min Act: -0.0000

Data Index: 1217650 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.5427. Min Act: -0.0000

Data Index: 886844 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.2652. Min Act: -0.0000

Data Index: 771954 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 1.5427. Min Range: -1.5427

Max Act: 1.0349. Min Act: -0.0000

Data Index: 114336 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.8413. Min Act: -0.0000

Data Index: 1592828 (Python Code)

Max Activating Token Index: 188

Text #6

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.8587. Min Act: -0.0000

Data Index: 772836 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.7458. Min Act: -0.0000

Data Index: 1083897 (C4 (Web Text))

Max Activating Token Index: 798

Text #8

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.8112. Min Act: -0.0000

Data Index: 1410794 (Python Code)

Max Activating Token Index: 711

Text #9

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.6961. Min Act: -0.0000

Data Index: 338814 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.7046. Min Act: -0.0000

Data Index: 1624246 (Python Code)

Max Activating Token Index: 325

Text #11

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.7558. Min Act: -0.0000

Data Index: 1426926 (Python Code)

Max Activating Token Index: 736

Text #12

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.7773. Min Act: -0.0000

Data Index: 1594458 (Python Code)

Max Activating Token Index: 479

Text #13

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.6930. Min Act: -0.0000

Data Index: 1481815 (Python Code)

Max Activating Token Index: 123

Text #14

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.6960. Min Act: -0.0000

Data Index: 1458457 (Python Code)

Max Activating Token Index: 509

Text #15

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.7606. Min Act: -0.0000

Data Index: 1484487 (Python Code)

Max Activating Token Index: 900

Text #16

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1604512 (Python Code)

Max Activating Token Index: 30

Text #17

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.6281. Min Act: -0.0000

Data Index: 1612011 (Python Code)

Max Activating Token Index: 629

Text #18

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.6325. Min Act: -0.0000

Data Index: 837252 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 1.5427. Min Range: -1.5427

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1442407 (Python Code)

Max Activating Token Index: 809