Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 864 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0292. Min Act: -0.0006

Data Index: 738298 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0259. Min Act: -0.0006

Data Index: 1036030 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0268. Min Act: -0.0006

Data Index: 337186 (C4 (Web Text))

Max Activating Token Index: 953

Text #3

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0260. Min Act: -0.0006

Data Index: 883635 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0252. Min Act: -0.0006

Data Index: 1137501 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0257. Min Act: -0.0006

Data Index: 836661 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0249. Min Act: -0.0006

Data Index: 1211715 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0250. Min Act: -0.0006

Data Index: 1500626 (Python Code)

Max Activating Token Index: 420

Text #8

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0242. Min Act: -0.0006

Data Index: 718706 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0242. Min Act: -0.0006

Data Index: 1640050 (Python Code)

Max Activating Token Index: 584

Text #10

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0228. Min Act: -0.0006

Data Index: 1020619 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0236. Min Act: -0.0006

Data Index: 1103178 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0244. Min Act: -0.0006

Data Index: 42785 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0250. Min Act: -0.0006

Data Index: 871674 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0240. Min Act: -0.0006

Data Index: 43735 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0244. Min Act: -0.0006

Data Index: 417538 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0243. Min Act: -0.0006

Data Index: 121973 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0253. Min Act: -0.0006

Data Index: 1574366 (Python Code)

Max Activating Token Index: 921

Text #18

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0235. Min Act: -0.0006

Data Index: 519487 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1181226 (C4 (Web Text))

Max Activating Token Index: 395