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

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

Neuron 193 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.6412. Min Range: -9.6412

Max Act: 9.6412. Min Act: -0.0000

Data Index: 1525087 (Python Code)

Max Activating Token Index: 783

Text #1

Max Range: 9.6412. Min Range: -9.6412

Max Act: 9.5834. Min Act: -0.0000

Data Index: 1649321 (Python Code)

Max Activating Token Index: 311

Text #2

Max Range: 9.6412. Min Range: -9.6412

Max Act: 9.2255. Min Act: -0.0000

Data Index: 1368812 (Python Code)

Max Activating Token Index: 165

Text #3

Max Range: 9.6412. Min Range: -9.6412

Max Act: 9.3725. Min Act: -0.0000

Data Index: 1368368 (Python Code)

Max Activating Token Index: 725

Text #4

Max Range: 9.6412. Min Range: -9.6412

Max Act: 9.2659. Min Act: -0.0000

Data Index: 1596226 (Python Code)

Max Activating Token Index: 157

Text #5

Max Range: 9.6412. Min Range: -9.6412

Max Act: 9.2127. Min Act: -0.0000

Data Index: 1478208 (Python Code)

Max Activating Token Index: 266

Text #6

Max Range: 9.6412. Min Range: -9.6412

Max Act: 9.2177. Min Act: -0.0000

Data Index: 1513394 (Python Code)

Max Activating Token Index: 900

Text #7

Max Range: 9.6412. Min Range: -9.6412

Max Act: 9.1048. Min Act: -0.0000

Data Index: 1477210 (Python Code)

Max Activating Token Index: 496

Text #8

Max Range: 9.6412. Min Range: -9.6412

Max Act: 9.2219. Min Act: -0.0000

Data Index: 1502995 (Python Code)

Max Activating Token Index: 936

Text #9

Max Range: 9.6412. Min Range: -9.6412

Max Act: 9.1348. Min Act: -0.0000

Data Index: 1398104 (Python Code)

Max Activating Token Index: 101

Text #10

Max Range: 9.6412. Min Range: -9.6412

Max Act: 8.8770. Min Act: -0.0000

Data Index: 1638390 (Python Code)

Max Activating Token Index: 247

Text #11

Max Range: 9.6412. Min Range: -9.6412

Max Act: 8.8813. Min Act: -0.0000

Data Index: 1490546 (Python Code)

Max Activating Token Index: 482

Text #12

Max Range: 9.6412. Min Range: -9.6412

Max Act: 8.7610. Min Act: -0.0000

Data Index: 1468884 (Python Code)

Max Activating Token Index: 850

Text #13

Max Range: 9.6412. Min Range: -9.6412

Max Act: 8.8705. Min Act: -0.0000

Data Index: 1411302 (Python Code)

Max Activating Token Index: 56

Text #14

Max Range: 9.6412. Min Range: -9.6412

Max Act: 8.4156. Min Act: -0.0000

Data Index: 1492924 (Python Code)

Max Activating Token Index: 298

Text #15

Max Range: 9.6412. Min Range: -9.6412

Max Act: 8.6798. Min Act: -0.0000

Data Index: 1518767 (Python Code)

Max Activating Token Index: 451

Text #16

Max Range: 9.6412. Min Range: -9.6412

Max Act: 8.4436. Min Act: -0.0000

Data Index: 1534298 (Python Code)

Max Activating Token Index: 704

Text #17

Max Range: 9.6412. Min Range: -9.6412

Max Act: 8.5507. Min Act: -0.0000

Data Index: 1641718 (Python Code)

Max Activating Token Index: 110

Text #18

Max Range: 9.6412. Min Range: -9.6412

Max Act: 8.1490. Min Act: -0.0000

Data Index: 1428272 (Python Code)

Max Activating Token Index: 563

Text #19

Max Range: 9.6412. Min Range: -9.6412

Max Act: 8.2395. Min Act: -0.0000

Data Index: 1649046 (Python Code)

Max Activating Token Index: 801