Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 257 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0185. Min Act: -0.0005

Data Index: 521872 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0186. Min Act: -0.0005

Data Index: 647486 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0169. Min Act: -0.0005

Data Index: 542284 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0159. Min Act: -0.0005

Data Index: 84438 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0158. Min Act: -0.0005

Data Index: 629949 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0152. Min Act: -0.0005

Data Index: 402388 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0145. Min Act: -0.0005

Data Index: 757969 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0149. Min Act: -0.0005

Data Index: 55192 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0142. Min Act: -0.0005

Data Index: 492404 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0150. Min Act: -0.0005

Data Index: 291424 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0148. Min Act: -0.0005

Data Index: 618992 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0146. Min Act: -0.0005

Data Index: 936671 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0145. Min Act: -0.0005

Data Index: 131895 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0137. Min Act: -0.0005

Data Index: 936797 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0140. Min Act: -0.0005

Data Index: 1158716 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0137. Min Act: -0.0005

Data Index: 251787 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0144. Min Act: -0.0005

Data Index: 825584 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0147. Min Act: -0.0005

Data Index: 345141 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0140. Min Act: -0.0005

Data Index: 114709 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0137. Min Act: -0.0005

Data Index: 1585980 (Python Code)

Max Activating Token Index: 861