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

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

Neuron 843 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0287. Min Act: -0.0001

Data Index: 246861 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0001

Data Index: 721199 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0299. Min Act: -0.0001

Data Index: 1199381 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0291. Min Act: -0.0001

Data Index: 1566764 (Python Code)

Max Activating Token Index: 281

Text #4

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0290. Min Act: -0.0001

Data Index: 532989 (C4 (Web Text))

Max Activating Token Index: 281

Text #5

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0277. Min Act: -0.0001

Data Index: 512788 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0283. Min Act: -0.0001

Data Index: 33396 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0284. Min Act: -0.0001

Data Index: 732685 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0279. Min Act: -0.0001

Data Index: 1531148 (Python Code)

Max Activating Token Index: 336

Text #9

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0286. Min Act: -0.0001

Data Index: 722637 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0273. Min Act: -0.0001

Data Index: 424338 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0264. Min Act: -0.0001

Data Index: 220308 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0249. Min Act: -0.0001

Data Index: 1055008 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0218. Min Act: -0.0001

Data Index: 549306 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0237. Min Act: -0.0001

Data Index: 1097186 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0271. Min Act: -0.0001

Data Index: 219180 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0260. Min Act: -0.0001

Data Index: 162354 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0256. Min Act: -0.0001

Data Index: 1520307 (Python Code)

Max Activating Token Index: 436

Text #18

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0268. Min Act: -0.0001

Data Index: 1014505 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0251. Min Act: -0.0001

Data Index: 1140267 (C4 (Web Text))

Max Activating Token Index: 66