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

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

Neuron 3689 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1654567 (Python Code)

Max Activating Token Index: 616

Text #1

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1491397 (Python Code)

Max Activating Token Index: 843

Text #2

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0290. Min Act: -0.0002

Data Index: 1131686 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0281. Min Act: -0.0002

Data Index: 1191974 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0254. Min Act: -0.0002

Data Index: 388950 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0265. Min Act: -0.0002

Data Index: 7371 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0239. Min Act: -0.0002

Data Index: 457936 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0258. Min Act: -0.0002

Data Index: 23879 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0257. Min Act: -0.0002

Data Index: 138696 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0239. Min Act: -0.0002

Data Index: 1559719 (Python Code)

Max Activating Token Index: 911

Text #10

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1652520 (Python Code)

Max Activating Token Index: 762

Text #11

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0250. Min Act: -0.0002

Data Index: 619267 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1356445 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0244. Min Act: -0.0002

Data Index: 1095184 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0259. Min Act: -0.0002

Data Index: 590897 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1368621 (Python Code)

Max Activating Token Index: 494

Text #16

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0237. Min Act: -0.0002

Data Index: 247188 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1124878 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0259. Min Act: -0.0002

Data Index: 1492310 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1457386 (Python Code)

Max Activating Token Index: 936