Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4600 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0447. Min Act: -0.0003

Data Index: 550881 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0262. Min Act: -0.0003

Data Index: 843192 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0286. Min Act: -0.0002

Data Index: 509258 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0327. Min Act: -0.0003

Data Index: 952922 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0278. Min Act: -0.0003

Data Index: 580365 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0247. Min Act: -0.0002

Data Index: 1149840 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0244. Min Act: -0.0003

Data Index: 647735 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0253. Min Act: -0.0003

Data Index: 335060 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0256. Min Act: -0.0003

Data Index: 885114 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0263. Min Act: -0.0002

Data Index: 581350 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0267. Min Act: -0.0003

Data Index: 32639 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0241. Min Act: -0.0003

Data Index: 284347 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0251. Min Act: -0.0003

Data Index: 681178 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0204. Min Act: -0.0002

Data Index: 786110 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1074988 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1284681 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0222. Min Act: -0.0003

Data Index: 982319 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0232. Min Act: -0.0003

Data Index: 217567 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0279. Min Act: -0.0003

Data Index: 364112 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 0.0447. Min Range: -0.0447

Max Act: 0.0209. Min Act: -0.0003

Data Index: 327892 (C4 (Web Text))

Max Activating Token Index: 308