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

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

Neuron 1522 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: 0.0349. Min Range: -0.0349

Max Act: 0.0349. Min Act: -0.0003

Data Index: 968830 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0327. Min Act: -0.0002

Data Index: 715124 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0319. Min Act: -0.0003

Data Index: 42279 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0302. Min Act: -0.0003

Data Index: 1032750 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0290. Min Act: -0.0002

Data Index: 254239 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0283. Min Act: -0.0002

Data Index: 641443 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0280. Min Act: -0.0003

Data Index: 898568 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0258. Min Act: -0.0002

Data Index: 746707 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0267. Min Act: -0.0003

Data Index: 1241597 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0263. Min Act: -0.0002

Data Index: 572263 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0252. Min Act: -0.0003

Data Index: 1303861 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0253. Min Act: -0.0003

Data Index: 968452 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0238. Min Act: -0.0002

Data Index: 1128292 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0226. Min Act: -0.0002

Data Index: 401682 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0215. Min Act: -0.0002

Data Index: 544205 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0222. Min Act: -0.0003

Data Index: 1444237 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0222. Min Act: -0.0002

Data Index: 38789 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0225. Min Act: -0.0003

Data Index: 1531704 (Python Code)

Max Activating Token Index: 58

Text #18

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1317917 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.0349. Min Range: -0.0349

Max Act: 0.0224. Min Act: -0.0002

Data Index: 166973 (C4 (Web Text))

Max Activating Token Index: 756