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

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

Neuron 4399 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: 0.0390. Min Range: -0.0390

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1235983 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0370. Min Act: -0.0003

Data Index: 916602 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0311. Min Act: -0.0002

Data Index: 116980 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0318. Min Act: -0.0003

Data Index: 1198364 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0295. Min Act: -0.0002

Data Index: 643168 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0276. Min Act: -0.0002

Data Index: 225928 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0278. Min Act: -0.0003

Data Index: 844635 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0272. Min Act: -0.0002

Data Index: 1130061 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0270. Min Act: -0.0003

Data Index: 733240 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0259. Min Act: -0.0003

Data Index: 836621 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0265. Min Act: -0.0002

Data Index: 129705 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0253. Min Act: -0.0003

Data Index: 452111 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0261. Min Act: -0.0002

Data Index: 129380 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0265. Min Act: -0.0003

Data Index: 1214552 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1058322 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0269. Min Act: -0.0003

Data Index: 501618 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0263. Min Act: -0.0003

Data Index: 395830 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1117120 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0254. Min Act: -0.0002

Data Index: 153617 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0247. Min Act: -0.0002

Data Index: 221809 (C4 (Web Text))

Max Activating Token Index: 947