Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1750 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0342. Min Act: -0.0004

Data Index: 1270392 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0334. Min Act: -0.0005

Data Index: 1122984 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0334. Min Act: -0.0004

Data Index: 339007 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0329. Min Act: -0.0004

Data Index: 1187058 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0321. Min Act: -0.0005

Data Index: 750103 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0311. Min Act: -0.0004

Data Index: 246933 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0316. Min Act: -0.0004

Data Index: 889921 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0313. Min Act: -0.0005

Data Index: 839641 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0296. Min Act: -0.0004

Data Index: 1016012 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0301. Min Act: -0.0004

Data Index: 436480 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0295. Min Act: -0.0005

Data Index: 114323 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0299. Min Act: -0.0005

Data Index: 138189 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0299. Min Act: -0.0005

Data Index: 1168024 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0295. Min Act: -0.0005

Data Index: 615368 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0292. Min Act: -0.0004

Data Index: 297463 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0286. Min Act: -0.0005

Data Index: 320181 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0291. Min Act: -0.0004

Data Index: 443951 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0291. Min Act: -0.0004

Data Index: 325901 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0290. Min Act: -0.0005

Data Index: 802191 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.0342. Min Range: -0.0342

Max Act: 0.0290. Min Act: -0.0005

Data Index: 281214 (C4 (Web Text))

Max Activating Token Index: 833