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

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

Neuron 2455 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: 0.0328. Min Range: -0.0328

Max Act: 0.0326. Min Act: -0.0003

Data Index: 750658 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0318. Min Act: -0.0003

Data Index: 235112 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0328. Min Act: -0.0003

Data Index: 776549 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0283. Min Act: -0.0003

Data Index: 208258 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0289. Min Act: -0.0003

Data Index: 526840 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0279. Min Act: -0.0003

Data Index: 716334 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0282. Min Act: -0.0003

Data Index: 694992 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0287. Min Act: -0.0003

Data Index: 750238 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0231. Min Act: -0.0003

Data Index: 903605 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0264. Min Act: -0.0003

Data Index: 579918 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0234. Min Act: -0.0003

Data Index: 691095 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0238. Min Act: -0.0003

Data Index: 37699 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0261. Min Act: -0.0003

Data Index: 106999 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0217. Min Act: -0.0003

Data Index: 65709 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0238. Min Act: -0.0003

Data Index: 666367 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0221. Min Act: -0.0003

Data Index: 22776 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0225. Min Act: -0.0003

Data Index: 72686 (C4 (Web Text))

Max Activating Token Index: 911

Text #17

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0220. Min Act: -0.0004

Data Index: 350761 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0234. Min Act: -0.0003

Data Index: 996014 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0209. Min Act: -0.0003

Data Index: 1193479 (C4 (Web Text))

Max Activating Token Index: 444