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

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

Neuron 1724 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: 0.0401. Min Range: -0.0401

Max Act: 0.0371. Min Act: -0.0003

Data Index: 450757 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0401. Min Act: -0.0003

Data Index: 525857 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0392. Min Act: -0.0003

Data Index: 1043137 (C4 (Web Text))

Max Activating Token Index: 431

Text #3

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0355. Min Act: -0.0003

Data Index: 1202639 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0350. Min Act: -0.0003

Data Index: 608686 (C4 (Web Text))

Max Activating Token Index: 448

Text #5

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1142081 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0328. Min Act: -0.0003

Data Index: 402796 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0349. Min Act: -0.0003

Data Index: 892675 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0338. Min Act: -0.0003

Data Index: 678542 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1160535 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0338. Min Act: -0.0004

Data Index: 871670 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0343. Min Act: -0.0003

Data Index: 685607 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0352. Min Act: -0.0003

Data Index: 1140338 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0334. Min Act: -0.0003

Data Index: 894452 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0354. Min Act: -0.0003

Data Index: 812987 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0326. Min Act: -0.0004

Data Index: 681068 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0331. Min Act: -0.0003

Data Index: 1286914 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0304. Min Act: -0.0003

Data Index: 493847 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0329. Min Act: -0.0003

Data Index: 1127222 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.0401. Min Range: -0.0401

Max Act: 0.0322. Min Act: -0.0004

Data Index: 451417 (C4 (Web Text))

Max Activating Token Index: 732