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

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

Neuron 3930 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: 0.1562. Min Range: -0.1562

Max Act: 0.1523. Min Act: -0.0003

Data Index: 278729 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1553. Min Act: -0.0003

Data Index: 1339497 (C4 (Web Text))

Max Activating Token Index: 911

Text #2

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1451. Min Act: -0.0003

Data Index: 1102090 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1377. Min Act: -0.0003

Data Index: 1302824 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1483. Min Act: -0.0003

Data Index: 203555 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1501. Min Act: -0.0003

Data Index: 852639 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1380. Min Act: -0.0003

Data Index: 826325 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1424. Min Act: -0.0003

Data Index: 787888 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1372. Min Act: -0.0003

Data Index: 1164007 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1562. Min Act: -0.0003

Data Index: 762302 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1317. Min Act: -0.0003

Data Index: 804028 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1265. Min Act: -0.0003

Data Index: 805628 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1357. Min Act: -0.0003

Data Index: 865410 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1207. Min Act: -0.0003

Data Index: 683834 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1324. Min Act: -0.0003

Data Index: 89164 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1381. Min Act: -0.0003

Data Index: 102464 (C4 (Web Text))

Max Activating Token Index: 623

Text #16

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1334. Min Act: -0.0003

Data Index: 259016 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1185. Min Act: -0.0003

Data Index: 863790 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1200. Min Act: -0.0003

Data Index: 33432 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 0.1562. Min Range: -0.1562

Max Act: 0.1353. Min Act: -0.0003

Data Index: 1336847 (C4 (Web Text))

Max Activating Token Index: 95