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

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

Neuron 699 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: 0.0323. Min Range: -0.0323

Max Act: 0.0323. Min Act: -0.0003

Data Index: 386020 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0295. Min Act: -0.0003

Data Index: 314275 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0310. Min Act: -0.0003

Data Index: 639749 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0296. Min Act: -0.0003

Data Index: 205509 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0292. Min Act: -0.0003

Data Index: 493243 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0287. Min Act: -0.0004

Data Index: 870860 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0282. Min Act: -0.0004

Data Index: 136826 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0280. Min Act: -0.0003

Data Index: 781238 (C4 (Web Text))

Max Activating Token Index: 460

Text #8

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0272. Min Act: -0.0003

Data Index: 841336 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0267. Min Act: -0.0003

Data Index: 363377 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0266. Min Act: -0.0003

Data Index: 712198 (C4 (Web Text))

Max Activating Token Index: 8

Text #11

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0264. Min Act: -0.0003

Data Index: 634945 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0254. Min Act: -0.0003

Data Index: 762988 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0247. Min Act: -0.0003

Data Index: 135482 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0252. Min Act: -0.0003

Data Index: 567067 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0246. Min Act: -0.0003

Data Index: 519813 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0245. Min Act: -0.0003

Data Index: 296977 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0249. Min Act: -0.0003

Data Index: 294326 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0242. Min Act: -0.0003

Data Index: 1066296 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0256. Min Act: -0.0003

Data Index: 8493 (C4 (Web Text))

Max Activating Token Index: 163