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

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

Neuron 350 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1226217 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0258. Min Act: -0.0002

Data Index: 1084951 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1176052 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0260. Min Act: -0.0003

Data Index: 986025 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0238. Min Act: -0.0003

Data Index: 743287 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1380846 (Python Code)

Max Activating Token Index: 835

Text #6

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0247. Min Act: -0.0002

Data Index: 651453 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1291168 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0239. Min Act: -0.0003

Data Index: 483378 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0245. Min Act: -0.0003

Data Index: 1380554 (Python Code)

Max Activating Token Index: 640

Text #10

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1041054 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1436918 (Python Code)

Max Activating Token Index: 650

Text #12

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1519910 (Python Code)

Max Activating Token Index: 620

Text #13

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1370752 (Python Code)

Max Activating Token Index: 399

Text #14

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1561866 (Python Code)

Max Activating Token Index: 476

Text #15

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0226. Min Act: -0.0003

Data Index: 1503412 (Python Code)

Max Activating Token Index: 199

Text #16

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1434091 (Python Code)

Max Activating Token Index: 383

Text #17

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1531351 (Python Code)

Max Activating Token Index: 593

Text #18

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1372362 (Python Code)

Max Activating Token Index: 410

Text #19

Max Range: 0.0270. Min Range: -0.0270

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1446191 (Python Code)

Max Activating Token Index: 370