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

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

Neuron 1939 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.5289. Min Act: -0.0000

Data Index: 1412732 (Python Code)

Max Activating Token Index: 257

Text #1

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.4662. Min Act: -0.0001

Data Index: 1474362 (Python Code)

Max Activating Token Index: 933

Text #2

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.5317. Min Act: -0.0000

Data Index: 1592578 (Python Code)

Max Activating Token Index: 391

Text #3

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.5133. Min Act: -0.0000

Data Index: 1644543 (Python Code)

Max Activating Token Index: 26

Text #4

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.4960. Min Act: -0.0000

Data Index: 1497051 (Python Code)

Max Activating Token Index: 463

Text #5

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.5039. Min Act: -0.0000

Data Index: 1474788 (Python Code)

Max Activating Token Index: 133

Text #6

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.5021. Min Act: -0.0000

Data Index: 1629856 (Python Code)

Max Activating Token Index: 215

Text #7

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.4750. Min Act: -0.0000

Data Index: 1389266 (Python Code)

Max Activating Token Index: 945

Text #8

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1406365 (Python Code)

Max Activating Token Index: 635

Text #9

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1481734 (Python Code)

Max Activating Token Index: 507

Text #10

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1462437 (Python Code)

Max Activating Token Index: 256

Text #11

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1650774 (Python Code)

Max Activating Token Index: 427

Text #12

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.5115. Min Act: -0.0001

Data Index: 1521804 (Python Code)

Max Activating Token Index: 772

Text #13

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.4590. Min Act: -0.0000

Data Index: 1585011 (Python Code)

Max Activating Token Index: 734

Text #14

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.4694. Min Act: -0.0000

Data Index: 1569773 (Python Code)

Max Activating Token Index: 354

Text #15

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.4295. Min Act: -0.0000

Data Index: 1460314 (Python Code)

Max Activating Token Index: 745

Text #16

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.4497. Min Act: -0.0001

Data Index: 1613764 (Python Code)

Max Activating Token Index: 244

Text #17

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.4482. Min Act: -0.0000

Data Index: 1648791 (Python Code)

Max Activating Token Index: 544

Text #18

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.4232. Min Act: -0.0001

Data Index: 1489336 (Python Code)

Max Activating Token Index: 757

Text #19

Max Range: 0.5317. Min Range: -0.5317

Max Act: 0.4301. Min Act: -0.0000

Data Index: 1459527 (Python Code)

Max Activating Token Index: 229