Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 756 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1261848 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1302496 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0265. Min Act: -0.0002

Data Index: 429823 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0271. Min Act: -0.0002

Data Index: 748395 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0265. Min Act: -0.0003

Data Index: 300087 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0265. Min Act: -0.0002

Data Index: 110713 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0266. Min Act: -0.0002

Data Index: 707174 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0273. Min Act: -0.0003

Data Index: 1229802 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0267. Min Act: -0.0002

Data Index: 597147 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0266. Min Act: -0.0003

Data Index: 138049 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0253. Min Act: -0.0003

Data Index: 946511 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0255. Min Act: -0.0002

Data Index: 703173 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0257. Min Act: -0.0002

Data Index: 743159 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0257. Min Act: -0.0002

Data Index: 36149 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0253. Min Act: -0.0002

Data Index: 541056 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0259. Min Act: -0.0003

Data Index: 499085 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0249. Min Act: -0.0003

Data Index: 1504620 (Python Code)

Max Activating Token Index: 505

Text #17

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0252. Min Act: -0.0002

Data Index: 530424 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0246. Min Act: -0.0002

Data Index: 44498 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0249. Min Act: -0.0002

Data Index: 880109 (C4 (Web Text))

Max Activating Token Index: 546