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

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

Neuron 187 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1256. Min Range: -7.1256

Max Act: 7.1256. Min Act: -0.0000

Data Index: 1483492 (Python Code)

Max Activating Token Index: 398

Text #1

Max Range: 7.1256. Min Range: -7.1256

Max Act: 6.6383. Min Act: 0.0000

Data Index: 1644154 (Python Code)

Max Activating Token Index: 664

Text #2

Max Range: 7.1256. Min Range: -7.1256

Max Act: 6.3002. Min Act: 0.0001

Data Index: 1397677 (Python Code)

Max Activating Token Index: 255

Text #3

Max Range: 7.1256. Min Range: -7.1256

Max Act: 6.3358. Min Act: -0.0000

Data Index: 1363021 (Python Code)

Max Activating Token Index: 347

Text #4

Max Range: 7.1256. Min Range: -7.1256

Max Act: 6.1321. Min Act: 0.0000

Data Index: 1561702 (Python Code)

Max Activating Token Index: 131

Text #5

Max Range: 7.1256. Min Range: -7.1256

Max Act: 6.1374. Min Act: 0.0000

Data Index: 1463581 (Python Code)

Max Activating Token Index: 174

Text #6

Max Range: 7.1256. Min Range: -7.1256

Max Act: 6.1056. Min Act: 0.0000

Data Index: 1499525 (Python Code)

Max Activating Token Index: 806

Text #7

Max Range: 7.1256. Min Range: -7.1256

Max Act: 6.0771. Min Act: -0.0000

Data Index: 1361704 (Python Code)

Max Activating Token Index: 554

Text #8

Max Range: 7.1256. Min Range: -7.1256

Max Act: 5.9480. Min Act: 0.0001

Data Index: 1627284 (Python Code)

Max Activating Token Index: 122

Text #9

Max Range: 7.1256. Min Range: -7.1256

Max Act: 5.9371. Min Act: -0.0000

Data Index: 1404097 (Python Code)

Max Activating Token Index: 548

Text #10

Max Range: 7.1256. Min Range: -7.1256

Max Act: 5.9272. Min Act: 0.0002

Data Index: 1630463 (Python Code)

Max Activating Token Index: 419

Text #11

Max Range: 7.1256. Min Range: -7.1256

Max Act: 6.0889. Min Act: 0.0002

Data Index: 1516629 (Python Code)

Max Activating Token Index: 939

Text #12

Max Range: 7.1256. Min Range: -7.1256

Max Act: 5.8428. Min Act: -0.0000

Data Index: 1376081 (Python Code)

Max Activating Token Index: 182

Text #13

Max Range: 7.1256. Min Range: -7.1256

Max Act: 5.6314. Min Act: 0.0000

Data Index: 1622958 (Python Code)

Max Activating Token Index: 280

Text #14

Max Range: 7.1256. Min Range: -7.1256

Max Act: 5.6198. Min Act: 0.0002

Data Index: 1448867 (Python Code)

Max Activating Token Index: 657

Text #15

Max Range: 7.1256. Min Range: -7.1256

Max Act: 5.5805. Min Act: 0.0001

Data Index: 1518300 (Python Code)

Max Activating Token Index: 342

Text #16

Max Range: 7.1256. Min Range: -7.1256

Max Act: 5.7219. Min Act: 0.0000

Data Index: 1580852 (Python Code)

Max Activating Token Index: 130

Text #17

Max Range: 7.1256. Min Range: -7.1256

Max Act: 5.6229. Min Act: -0.0000

Data Index: 1367048 (Python Code)

Max Activating Token Index: 327

Text #18

Max Range: 7.1256. Min Range: -7.1256

Max Act: 5.6260. Min Act: 0.0001

Data Index: 1480189 (Python Code)

Max Activating Token Index: 750

Text #19

Max Range: 7.1256. Min Range: -7.1256

Max Act: 5.5546. Min Act: 0.0002

Data Index: 1407771 (Python Code)

Max Activating Token Index: 273