Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 224 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0395. Min Act: -0.0003

Data Index: 695694 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1234288 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1309722 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0275. Min Act: -0.0003

Data Index: 56267 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0270. Min Act: -0.0003

Data Index: 8703 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0271. Min Act: -0.0003

Data Index: 1283877 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0265. Min Act: -0.0003

Data Index: 763351 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0257. Min Act: -0.0003

Data Index: 777013 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0252. Min Act: -0.0003

Data Index: 685896 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0257. Min Act: -0.0003

Data Index: 1295791 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0264. Min Act: -0.0003

Data Index: 952099 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0239. Min Act: -0.0003

Data Index: 1240463 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0220. Min Act: -0.0003

Data Index: 190363 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0249. Min Act: -0.0003

Data Index: 729798 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0244. Min Act: -0.0003

Data Index: 300568 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0247. Min Act: -0.0003

Data Index: 295441 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0239. Min Act: -0.0003

Data Index: 88721 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0224. Min Act: -0.0003

Data Index: 148266 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0238. Min Act: -0.0003

Data Index: 271868 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0230. Min Act: -0.0003

Data Index: 1299045 (C4 (Web Text))

Max Activating Token Index: 740