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

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

Neuron 4375 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0294. Min Act: -0.0002

Data Index: 532199 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0274. Min Act: -0.0001

Data Index: 1501516 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0272. Min Act: -0.0002

Data Index: 1121790 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0269. Min Act: -0.0001

Data Index: 1450525 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0268. Min Act: -0.0001

Data Index: 1457998 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0261. Min Act: -0.0001

Data Index: 1636457 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0270. Min Act: -0.0001

Data Index: 1625564 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0259. Min Act: -0.0002

Data Index: 280016 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0262. Min Act: -0.0001

Data Index: 1507789 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0264. Min Act: -0.0001

Data Index: 1598266 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0255. Min Act: -0.0001

Data Index: 1469459 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1577349 (Python Code)

Max Activating Token Index: 291

Text #12

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0225. Min Act: -0.0002

Data Index: 102807 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0219. Min Act: -0.0001

Data Index: 437048 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0217. Min Act: -0.0002

Data Index: 1149675 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0217. Min Act: -0.0002

Data Index: 551651 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1229372 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0213. Min Act: -0.0002

Data Index: 374643 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0212. Min Act: -0.0001

Data Index: 1286231 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0211. Min Act: -0.0002

Data Index: 805162 (C4 (Web Text))

Max Activating Token Index: 265