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

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

Neuron 481 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: 0.0379. Min Range: -0.0379

Max Act: 0.0379. Min Act: -0.0003

Data Index: 417314 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0328. Min Act: -0.0004

Data Index: 35000 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0344. Min Act: -0.0003

Data Index: 846464 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0302. Min Act: -0.0003

Data Index: 207614 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0299. Min Act: -0.0003

Data Index: 921950 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0294. Min Act: -0.0003

Data Index: 788256 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0273. Min Act: -0.0003

Data Index: 278356 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0267. Min Act: -0.0003

Data Index: 1165988 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0258. Min Act: -0.0003

Data Index: 210083 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0272. Min Act: -0.0003

Data Index: 778625 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0261. Min Act: -0.0003

Data Index: 608858 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0266. Min Act: -0.0003

Data Index: 111422 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0255. Min Act: -0.0003

Data Index: 582200 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0242. Min Act: -0.0003

Data Index: 650910 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0243. Min Act: -0.0003

Data Index: 661529 (C4 (Web Text))

Max Activating Token Index: 305

Text #15

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0229. Min Act: -0.0003

Data Index: 751447 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0241. Min Act: -0.0003

Data Index: 438586 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0245. Min Act: -0.0003

Data Index: 1015633 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0243. Min Act: -0.0003

Data Index: 678837 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0228. Min Act: -0.0003

Data Index: 450166 (C4 (Web Text))

Max Activating Token Index: 301