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

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

Neuron 2945 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: 0.1589. Min Range: -0.1589

Max Act: 0.1589. Min Act: -0.0003

Data Index: 85445 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1539. Min Act: -0.0003

Data Index: 143879 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1381. Min Act: -0.0003

Data Index: 855340 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1392. Min Act: -0.0003

Data Index: 1287328 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1297. Min Act: -0.0003

Data Index: 512636 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1371. Min Act: -0.0003

Data Index: 524457 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1336. Min Act: -0.0003

Data Index: 813925 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1271. Min Act: -0.0003

Data Index: 1087275 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1213. Min Act: -0.0003

Data Index: 653378 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1166. Min Act: -0.0003

Data Index: 819282 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1192. Min Act: -0.0003

Data Index: 1232162 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1266. Min Act: -0.0003

Data Index: 940536 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1202. Min Act: -0.0003

Data Index: 950740 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1188. Min Act: -0.0003

Data Index: 92717 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1231. Min Act: -0.0003

Data Index: 1160483 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1266. Min Act: -0.0003

Data Index: 645680 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1210. Min Act: -0.0003

Data Index: 282596 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1058. Min Act: -0.0003

Data Index: 858821 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1080. Min Act: -0.0003

Data Index: 769213 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.1589. Min Range: -0.1589

Max Act: 0.1049. Min Act: -0.0003

Data Index: 330540 (C4 (Web Text))

Max Activating Token Index: 170