Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5148 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0338. Min Act: -0.0001

Data Index: 660358 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0232. Min Act: -0.0001

Data Index: 1569778 (Python Code)

Max Activating Token Index: 386

Text #2

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0212. Min Act: -0.0001

Data Index: 1007159 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0247. Min Act: -0.0001

Data Index: 432216 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0171. Min Act: -0.0001

Data Index: 1350082 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0224. Min Act: -0.0001

Data Index: 752074 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0223. Min Act: -0.0001

Data Index: 773583 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0188. Min Act: -0.0001

Data Index: 1560442 (Python Code)

Max Activating Token Index: 291

Text #8

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0213. Min Act: -0.0001

Data Index: 597607 (C4 (Web Text))

Max Activating Token Index: 461

Text #9

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0199. Min Act: -0.0001

Data Index: 1390697 (Python Code)

Max Activating Token Index: 572

Text #10

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0178. Min Act: -0.0001

Data Index: 1291979 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0211. Min Act: -0.0001

Data Index: 237982 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0178. Min Act: -0.0001

Data Index: 110010 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0184. Min Act: -0.0001

Data Index: 403227 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0169. Min Act: -0.0001

Data Index: 140279 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0197. Min Act: -0.0001

Data Index: 1619507 (Python Code)

Max Activating Token Index: 91

Text #16

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0178. Min Act: -0.0001

Data Index: 825331 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0182. Min Act: -0.0001

Data Index: 773739 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0198. Min Act: -0.0001

Data Index: 546304 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0179. Min Act: -0.0001

Data Index: 1460076 (Python Code)

Max Activating Token Index: 370