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

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

Neuron 3266 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: 0.0479. Min Range: -0.0479

Max Act: 0.0479. Min Act: -0.0002

Data Index: 612964 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0357. Min Act: -0.0002

Data Index: 654229 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1247347 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0306. Min Act: -0.0002

Data Index: 1225776 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0368. Min Act: -0.0002

Data Index: 202613 (C4 (Web Text))

Max Activating Token Index: 813

Text #5

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0342. Min Act: -0.0002

Data Index: 385004 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0335. Min Act: -0.0002

Data Index: 56916 (C4 (Web Text))

Max Activating Token Index: 652

Text #7

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0319. Min Act: -0.0002

Data Index: 999095 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0326. Min Act: -0.0002

Data Index: 982919 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0285. Min Act: -0.0002

Data Index: 185153 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0282. Min Act: -0.0002

Data Index: 127268 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0284. Min Act: -0.0002

Data Index: 82295 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1132143 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0279. Min Act: -0.0002

Data Index: 645782 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0297. Min Act: -0.0003

Data Index: 308407 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1175405 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0320. Min Act: -0.0002

Data Index: 848999 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1196399 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0274. Min Act: -0.0002

Data Index: 821699 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0247. Min Act: -0.0002

Data Index: 166325 (C4 (Web Text))

Max Activating Token Index: 291