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

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

Neuron 1694 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: 0.0277. Min Act: -0.0003

Data Index: 73996 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0259. Min Act: -0.0003

Data Index: 235830 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0248. Min Act: -0.0003

Data Index: 110694 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0254. Min Act: -0.0003

Data Index: 310854 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1101292 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0233. Min Act: -0.0003

Data Index: 834767 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0236. Min Act: -0.0003

Data Index: 890825 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0222. Min Act: -0.0003

Data Index: 600446 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0268. Min Act: -0.0003

Data Index: 368486 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0238. Min Act: -0.0003

Data Index: 1310244 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0245. Min Act: -0.0003

Data Index: 620483 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0212. Min Act: -0.0003

Data Index: 935442 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0200. Min Act: -0.0003

Data Index: 1030060 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0213. Min Act: -0.0003

Data Index: 270030 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0222. Min Act: -0.0003

Data Index: 135449 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0208. Min Act: -0.0003

Data Index: 1005547 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0211. Min Act: -0.0003

Data Index: 492032 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0202. Min Act: -0.0003

Data Index: 296615 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0197. Min Act: -0.0003

Data Index: 1103365 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.0277. Min Range: -0.0277

Max Act: 0.0202. Min Act: -0.0003

Data Index: 686905 (C4 (Web Text))

Max Activating Token Index: 473