Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 462 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0173. Min Act: -0.0006

Data Index: 507487 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0176. Min Act: -0.0006

Data Index: 1298590 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0165. Min Act: -0.0006

Data Index: 861246 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0161. Min Act: -0.0006

Data Index: 1069067 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0158. Min Act: -0.0006

Data Index: 1135787 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0149. Min Act: -0.0006

Data Index: 412416 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0155. Min Act: -0.0006

Data Index: 385081 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0154. Min Act: -0.0006

Data Index: 278326 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0148. Min Act: -0.0006

Data Index: 702495 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0151. Min Act: -0.0006

Data Index: 1120917 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0151. Min Act: -0.0006

Data Index: 153300 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0144. Min Act: -0.0006

Data Index: 354907 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0144. Min Act: -0.0006

Data Index: 602706 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0147. Min Act: -0.0006

Data Index: 1190847 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0147. Min Act: -0.0006

Data Index: 1140307 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0140. Min Act: -0.0006

Data Index: 344894 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0147. Min Act: -0.0006

Data Index: 1061629 (C4 (Web Text))

Max Activating Token Index: 780

Text #17

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0143. Min Act: -0.0006

Data Index: 222049 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0147. Min Act: -0.0006

Data Index: 968263 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0147. Min Act: -0.0006

Data Index: 1192352 (C4 (Web Text))

Max Activating Token Index: 697