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

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

Neuron 3017 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0328. Min Act: -0.0002

Data Index: 511579 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1344300 (C4 (Web Text))

Max Activating Token Index: 634

Text #2

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0296. Min Act: -0.0002

Data Index: 220719 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0305. Min Act: -0.0002

Data Index: 728323 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0264. Min Act: -0.0002

Data Index: 352436 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0240. Min Act: -0.0002

Data Index: 62968 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0252. Min Act: -0.0002

Data Index: 130961 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0250. Min Act: -0.0002

Data Index: 1297915 (C4 (Web Text))

Max Activating Token Index: 349

Text #8

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0250. Min Act: -0.0002

Data Index: 784707 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0247. Min Act: -0.0002

Data Index: 18413 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1304080 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0227. Min Act: -0.0002

Data Index: 424148 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0218. Min Act: -0.0002

Data Index: 2429 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0211. Min Act: -0.0002

Data Index: 939445 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0199. Min Act: -0.0002

Data Index: 971313 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0217. Min Act: -0.0002

Data Index: 1295793 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0228. Min Act: -0.0002

Data Index: 306751 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1182813 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0212. Min Act: -0.0002

Data Index: 784339 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0215. Min Act: -0.0002

Data Index: 78986 (C4 (Web Text))

Max Activating Token Index: 869