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

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

Neuron 4522 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.6609. Min Act: -0.0000

Data Index: 1404997 (Python Code)

Max Activating Token Index: 248

Text #1

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.7260. Min Act: -0.0000

Data Index: 1432000 (Python Code)

Max Activating Token Index: 39

Text #2

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.6207. Min Act: -0.0000

Data Index: 1536195 (Python Code)

Max Activating Token Index: 308

Text #3

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.4793. Min Act: -0.0000

Data Index: 1551117 (Python Code)

Max Activating Token Index: 458

Text #4

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.5059. Min Act: -0.0000

Data Index: 1401200 (Python Code)

Max Activating Token Index: 512

Text #5

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.4492. Min Act: -0.0000

Data Index: 1609761 (Python Code)

Max Activating Token Index: 95

Text #6

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.1746. Min Act: -0.0000

Data Index: 1565511 (Python Code)

Max Activating Token Index: 313

Text #7

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.2055. Min Act: -0.0000

Data Index: 1554829 (Python Code)

Max Activating Token Index: 395

Text #8

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.3575. Min Act: -0.0000

Data Index: 1460727 (Python Code)

Max Activating Token Index: 810

Text #9

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.0382. Min Act: -0.0000

Data Index: 55339 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.1576. Min Act: -0.0000

Data Index: 1459875 (Python Code)

Max Activating Token Index: 112

Text #11

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.0211. Min Act: -0.0000

Data Index: 1507359 (Python Code)

Max Activating Token Index: 409

Text #12

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.0176. Min Act: -0.0000

Data Index: 1440415 (Python Code)

Max Activating Token Index: 120

Text #13

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.0480. Min Act: -0.0000

Data Index: 1383025 (Python Code)

Max Activating Token Index: 255

Text #14

Max Range: 1.7260. Min Range: -1.7260

Max Act: 0.9330. Min Act: -0.0000

Data Index: 678416 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 1.7260. Min Range: -1.7260

Max Act: 1.0276. Min Act: -0.0000

Data Index: 1021500 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 1.7260. Min Range: -1.7260

Max Act: 0.9452. Min Act: -0.0000

Data Index: 1511273 (Python Code)

Max Activating Token Index: 615

Text #17

Max Range: 1.7260. Min Range: -1.7260

Max Act: 0.8623. Min Act: -0.0000

Data Index: 763288 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 1.7260. Min Range: -1.7260

Max Act: 0.7676. Min Act: -0.0000

Data Index: 349778 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 1.7260. Min Range: -1.7260

Max Act: 0.9062. Min Act: -0.0000

Data Index: 585928 (C4 (Web Text))

Max Activating Token Index: 110