Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2543 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1548. Min Act: -0.0000

Data Index: 787999 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1571. Min Act: -0.0000

Data Index: 385424 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1526. Min Act: -0.0000

Data Index: 329404 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1460. Min Act: -0.0000

Data Index: 322867 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1400. Min Act: -0.0000

Data Index: 383410 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1379. Min Act: -0.0000

Data Index: 847645 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1383. Min Act: -0.0000

Data Index: 795035 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1338. Min Act: -0.0000

Data Index: 390497 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1350. Min Act: -0.0000

Data Index: 1340536 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1281. Min Act: -0.0000

Data Index: 202931 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1280. Min Act: -0.0000

Data Index: 509594 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1260. Min Act: -0.0000

Data Index: 152038 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1257. Min Act: -0.0000

Data Index: 475525 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1203. Min Act: -0.0000

Data Index: 105555 (C4 (Web Text))

Max Activating Token Index: 588

Text #14

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1235. Min Act: -0.0000

Data Index: 1192243 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1214. Min Act: -0.0000

Data Index: 337066 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1263. Min Act: -0.0000

Data Index: 877085 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1152. Min Act: -0.0000

Data Index: 673839 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1194. Min Act: -0.0000

Data Index: 911257 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1191. Min Act: -0.0000

Data Index: 977274 (C4 (Web Text))

Max Activating Token Index: 398