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

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

Neuron 2801 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: 0.0371. Min Range: -0.0371

Max Act: 0.0347. Min Act: -0.0003

Data Index: 903224 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1917 (C4 (Web Text))

Max Activating Token Index: 864

Text #2

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0339. Min Act: -0.0003

Data Index: 1258986 (C4 (Web Text))

Max Activating Token Index: 375

Text #3

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0338. Min Act: -0.0003

Data Index: 88876 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0332. Min Act: -0.0003

Data Index: 223210 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0361. Min Act: -0.0003

Data Index: 829029 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0340. Min Act: -0.0003

Data Index: 267694 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0317. Min Act: -0.0003

Data Index: 939728 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0358. Min Act: -0.0003

Data Index: 496230 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0330. Min Act: -0.0003

Data Index: 113897 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0304. Min Act: -0.0003

Data Index: 757252 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0371. Min Act: -0.0004

Data Index: 57271 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0308. Min Act: -0.0003

Data Index: 937501 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0313. Min Act: -0.0003

Data Index: 56938 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0319. Min Act: -0.0003

Data Index: 955473 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0326. Min Act: -0.0003

Data Index: 1181425 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1055468 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0358. Min Act: -0.0003

Data Index: 950557 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0324. Min Act: -0.0003

Data Index: 663718 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.0371. Min Range: -0.0371

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1051610 (C4 (Web Text))

Max Activating Token Index: 640