Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2035 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0345. Min Act: -0.0002

Data Index: 26949 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0339. Min Act: -0.0002

Data Index: 681625 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0323. Min Act: -0.0002

Data Index: 962429 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0346. Min Act: -0.0002

Data Index: 393783 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0311. Min Act: -0.0002

Data Index: 882825 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0298. Min Act: -0.0003

Data Index: 605797 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0307. Min Act: -0.0002

Data Index: 545108 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1012348 (C4 (Web Text))

Max Activating Token Index: 65

Text #8

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0305. Min Act: -0.0002

Data Index: 533596 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0301. Min Act: -0.0003

Data Index: 418763 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0285. Min Act: -0.0002

Data Index: 893566 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0294. Min Act: -0.0002

Data Index: 466476 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0293. Min Act: -0.0003

Data Index: 901429 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0291. Min Act: -0.0002

Data Index: 99170 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0281. Min Act: -0.0002

Data Index: 1290327 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0285. Min Act: -0.0002

Data Index: 81285 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0278. Min Act: -0.0002

Data Index: 376417 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1250308 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0280. Min Act: -0.0002

Data Index: 533657 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.0346. Min Range: -0.0346

Max Act: 0.0282. Min Act: -0.0002

Data Index: 1155833 (C4 (Web Text))

Max Activating Token Index: 234