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

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

Neuron 2431 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: 0.0191. Min Range: -0.0191

Max Act: 0.0190. Min Act: -0.0003

Data Index: 1417448 (Python Code)

Max Activating Token Index: 827

Text #1

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0191. Min Act: -0.0003

Data Index: 1567235 (Python Code)

Max Activating Token Index: 743

Text #2

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0188. Min Act: -0.0003

Data Index: 1556255 (Python Code)

Max Activating Token Index: 645

Text #3

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0186. Min Act: -0.0003

Data Index: 291000 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0180. Min Act: -0.0003

Data Index: 729559 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0187. Min Act: -0.0003

Data Index: 1435437 (Python Code)

Max Activating Token Index: 551

Text #6

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0167. Min Act: -0.0003

Data Index: 1394669 (Python Code)

Max Activating Token Index: 549

Text #7

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0172. Min Act: -0.0003

Data Index: 1628744 (Python Code)

Max Activating Token Index: 325

Text #8

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0168. Min Act: -0.0003

Data Index: 365539 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0168. Min Act: -0.0003

Data Index: 327434 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0176. Min Act: -0.0003

Data Index: 551200 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0159. Min Act: -0.0003

Data Index: 826971 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0170. Min Act: -0.0003

Data Index: 626674 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0159. Min Act: -0.0003

Data Index: 1268324 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0160. Min Act: -0.0003

Data Index: 1563146 (Python Code)

Max Activating Token Index: 960

Text #15

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0164. Min Act: -0.0003

Data Index: 369109 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0155. Min Act: -0.0003

Data Index: 333619 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1558864 (Python Code)

Max Activating Token Index: 260

Text #18

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1264353 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.0191. Min Range: -0.0191

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1312835 (C4 (Web Text))

Max Activating Token Index: 803