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

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

Neuron 853 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0268. Min Act: -0.0004

Data Index: 643603 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0284. Min Act: -0.0004

Data Index: 1072079 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0228. Min Act: -0.0004

Data Index: 122396 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0240. Min Act: -0.0004

Data Index: 814319 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0227. Min Act: -0.0004

Data Index: 1297209 (C4 (Web Text))

Max Activating Token Index: 283

Text #5

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0228. Min Act: -0.0004

Data Index: 1217484 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0210. Min Act: -0.0004

Data Index: 83206 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0196. Min Act: -0.0004

Data Index: 915474 (C4 (Web Text))

Max Activating Token Index: 678

Text #8

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0202. Min Act: -0.0004

Data Index: 955127 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0206. Min Act: -0.0004

Data Index: 293334 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0219. Min Act: -0.0004

Data Index: 168615 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0209. Min Act: -0.0004

Data Index: 205477 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0201. Min Act: -0.0004

Data Index: 59749 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0208. Min Act: -0.0004

Data Index: 1281997 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0201. Min Act: -0.0004

Data Index: 453464 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0198. Min Act: -0.0004

Data Index: 664274 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0233. Min Act: -0.0004

Data Index: 969611 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0194. Min Act: -0.0004

Data Index: 1031586 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0213. Min Act: -0.0004

Data Index: 822655 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0208. Min Act: -0.0004

Data Index: 105982 (C4 (Web Text))

Max Activating Token Index: 294