Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 312 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0305. Min Act: -0.0003

Data Index: 831411 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0290. Min Act: -0.0003

Data Index: 162054 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0299. Min Act: -0.0003

Data Index: 481788 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0282. Min Act: -0.0004

Data Index: 130243 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0275. Min Act: -0.0003

Data Index: 572950 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0267. Min Act: -0.0003

Data Index: 1374107 (Python Code)

Max Activating Token Index: 310

Text #6

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0262. Min Act: -0.0003

Data Index: 1168269 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0254. Min Act: -0.0003

Data Index: 517745 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1569162 (Python Code)

Max Activating Token Index: 445

Text #9

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0255. Min Act: -0.0003

Data Index: 1439849 (Python Code)

Max Activating Token Index: 369

Text #10

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0259. Min Act: -0.0003

Data Index: 747338 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0251. Min Act: -0.0003

Data Index: 746315 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0252. Min Act: -0.0003

Data Index: 574424 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0254. Min Act: -0.0003

Data Index: 139573 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0250. Min Act: -0.0003

Data Index: 922202 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0247. Min Act: -0.0003

Data Index: 396360 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1513076 (Python Code)

Max Activating Token Index: 981

Text #17

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0245. Min Act: -0.0003

Data Index: 920940 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0251. Min Act: -0.0003

Data Index: 588577 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.0305. Min Range: -0.0305

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1154777 (C4 (Web Text))

Max Activating Token Index: 893