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

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

Neuron 2702 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: 0.0285. Min Range: -0.0285

Max Act: 0.0281. Min Act: -0.0003

Data Index: 978381 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0285. Min Act: -0.0003

Data Index: 484352 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0241. Min Act: -0.0003

Data Index: 158472 (C4 (Web Text))

Max Activating Token Index: 858

Text #3

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0246. Min Act: -0.0003

Data Index: 1594985 (Python Code)

Max Activating Token Index: 115

Text #4

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0254. Min Act: -0.0003

Data Index: 916823 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0234. Min Act: -0.0003

Data Index: 712059 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0260. Min Act: -0.0003

Data Index: 957648 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0238. Min Act: -0.0002

Data Index: 1524415 (Python Code)

Max Activating Token Index: 368

Text #8

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1075138 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0222. Min Act: -0.0003

Data Index: 127785 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0230. Min Act: -0.0003

Data Index: 1359582 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0225. Min Act: -0.0003

Data Index: 105711 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0212. Min Act: -0.0002

Data Index: 1447431 (Python Code)

Max Activating Token Index: 242

Text #13

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0223. Min Act: -0.0003

Data Index: 363555 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1547791 (Python Code)

Max Activating Token Index: 431

Text #15

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1362249 (Python Code)

Max Activating Token Index: 984

Text #16

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0210. Min Act: -0.0003

Data Index: 1150736 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0209. Min Act: -0.0003

Data Index: 498396 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0212. Min Act: -0.0003

Data Index: 393408 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 0.0285. Min Range: -0.0285

Max Act: 0.0204. Min Act: -0.0003

Data Index: 523491 (C4 (Web Text))

Max Activating Token Index: 274