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

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

Neuron 4317 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1597425 (Python Code)

Max Activating Token Index: 664

Text #1

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1505380 (Python Code)

Max Activating Token Index: 1013

Text #2

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0306. Min Act: -0.0002

Data Index: 1637729 (Python Code)

Max Activating Token Index: 73

Text #3

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0297. Min Act: -0.0002

Data Index: 1583234 (Python Code)

Max Activating Token Index: 326

Text #4

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0295. Min Act: -0.0002

Data Index: 492137 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1464528 (Python Code)

Max Activating Token Index: 52

Text #6

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1587848 (Python Code)

Max Activating Token Index: 414

Text #7

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0276. Min Act: -0.0002

Data Index: 782427 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1645852 (Python Code)

Max Activating Token Index: 609

Text #9

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1424938 (Python Code)

Max Activating Token Index: 945

Text #10

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1478418 (Python Code)

Max Activating Token Index: 786

Text #11

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0258. Min Act: -0.0002

Data Index: 1479837 (Python Code)

Max Activating Token Index: 88

Text #12

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1575032 (Python Code)

Max Activating Token Index: 747

Text #13

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1600144 (Python Code)

Max Activating Token Index: 389

Text #14

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0255. Min Act: -0.0002

Data Index: 1596558 (Python Code)

Max Activating Token Index: 641

Text #15

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1253403 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1005491 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0250. Min Act: -0.0002

Data Index: 480300 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0243. Min Act: -0.0002

Data Index: 1529574 (Python Code)

Max Activating Token Index: 69

Text #19

Max Range: 0.0340. Min Range: -0.0340

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1566574 (Python Code)

Max Activating Token Index: 115