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

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

Neuron 3640 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.7002. Min Act: -0.0000

Data Index: 1548010 (Python Code)

Max Activating Token Index: 144

Text #1

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.7599. Min Act: -0.0000

Data Index: 286977 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6270. Min Act: -0.0000

Data Index: 1510078 (Python Code)

Max Activating Token Index: 930

Text #3

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1303510 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.5270. Min Act: -0.0000

Data Index: 1622996 (Python Code)

Max Activating Token Index: 825

Text #5

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.5296. Min Act: -0.0000

Data Index: 1425869 (Python Code)

Max Activating Token Index: 82

Text #6

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.4877. Min Act: -0.0000

Data Index: 1598564 (Python Code)

Max Activating Token Index: 612

Text #7

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.4973. Min Act: -0.0000

Data Index: 1404178 (Python Code)

Max Activating Token Index: 414

Text #8

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.5249. Min Act: -0.0000

Data Index: 1448400 (Python Code)

Max Activating Token Index: 604

Text #9

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.5256. Min Act: -0.0000

Data Index: 1535952 (Python Code)

Max Activating Token Index: 527

Text #10

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.5412. Min Act: -0.0000

Data Index: 1551340 (Python Code)

Max Activating Token Index: 466

Text #11

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1111651 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.4774. Min Act: -0.0000

Data Index: 1414572 (Python Code)

Max Activating Token Index: 889

Text #13

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.5021. Min Act: -0.0000

Data Index: 1563433 (Python Code)

Max Activating Token Index: 440

Text #14

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.4230. Min Act: -0.0000

Data Index: 1406248 (Python Code)

Max Activating Token Index: 268

Text #15

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.4816. Min Act: -0.0000

Data Index: 1440424 (Python Code)

Max Activating Token Index: 707

Text #16

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.4773. Min Act: -0.0000

Data Index: 1226313 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.4899. Min Act: -0.0000

Data Index: 1515903 (Python Code)

Max Activating Token Index: 754

Text #18

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.4523. Min Act: -0.0000

Data Index: 1410195 (Python Code)

Max Activating Token Index: 694

Text #19

Max Range: 0.7599. Min Range: -0.7599

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1435808 (Python Code)

Max Activating Token Index: 530