Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 705 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2496. Min Act: -0.0003

Data Index: 89451 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2538. Min Act: -0.0003

Data Index: 32304 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2248. Min Act: -0.0003

Data Index: 724947 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2364. Min Act: -0.0003

Data Index: 18333 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2448. Min Act: -0.0003

Data Index: 70925 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2171. Min Act: -0.0003

Data Index: 1136768 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2275. Min Act: -0.0003

Data Index: 1215275 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2419. Min Act: -0.0003

Data Index: 900880 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2358. Min Act: -0.0003

Data Index: 1172813 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2181. Min Act: -0.0003

Data Index: 400762 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2274. Min Act: -0.0003

Data Index: 444668 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2303. Min Act: -0.0003

Data Index: 579032 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2182. Min Act: -0.0003

Data Index: 438601 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.1928. Min Act: -0.0003

Data Index: 826903 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2149. Min Act: -0.0003

Data Index: 1078230 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.1898. Min Act: -0.0003

Data Index: 496515 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2110. Min Act: -0.0003

Data Index: 1299040 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2259. Min Act: -0.0003

Data Index: 187796 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.2242. Min Act: -0.0003

Data Index: 1029238 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.2538. Min Range: -0.2538

Max Act: 0.1989. Min Act: -0.0003

Data Index: 161357 (C4 (Web Text))

Max Activating Token Index: 734