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

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

Neuron 1035 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: 0.0277. Min Range: -0.0277

Max Act: 0.0274. Min Act: -0.0003

Data Index: 28049 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0271. Min Act: -0.0003

Data Index: 1283984 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0275. Min Act: -0.0003

Data Index: 899636 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0277. Min Act: -0.0003

Data Index: 490865 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0235. Min Act: -0.0003

Data Index: 934433 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0269. Min Act: -0.0003

Data Index: 346806 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0243. Min Act: -0.0003

Data Index: 589334 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0258. Min Act: -0.0003

Data Index: 1343205 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0251. Min Act: -0.0003

Data Index: 294017 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1292946 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0248. Min Act: -0.0003

Data Index: 1092674 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0266. Min Act: -0.0003

Data Index: 239598 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0240. Min Act: -0.0003

Data Index: 435030 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0225. Min Act: -0.0003

Data Index: 1125202 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0242. Min Act: -0.0003

Data Index: 464415 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0242. Min Act: -0.0003

Data Index: 1138786 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0243. Min Act: -0.0003

Data Index: 365373 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0213. Min Act: -0.0003

Data Index: 1246436 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0240. Min Act: -0.0003

Data Index: 240733 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0223. Min Act: -0.0003

Data Index: 1119090 (C4 (Web Text))

Max Activating Token Index: 890