Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1236 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0196. Min Act: -0.0004

Data Index: 350921 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0174. Min Act: -0.0004

Data Index: 52052 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0173. Min Act: -0.0004

Data Index: 29668 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0173. Min Act: -0.0004

Data Index: 1063551 (C4 (Web Text))

Max Activating Token Index: 608

Text #4

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0172. Min Act: -0.0004

Data Index: 1192156 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0172. Min Act: -0.0004

Data Index: 1292668 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0167. Min Act: -0.0004

Data Index: 708839 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0171. Min Act: -0.0004

Data Index: 1313170 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0170. Min Act: -0.0004

Data Index: 725943 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0169. Min Act: -0.0004

Data Index: 842700 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0169. Min Act: -0.0004

Data Index: 1039083 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0167. Min Act: -0.0004

Data Index: 536994 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0167. Min Act: -0.0004

Data Index: 895158 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0163. Min Act: -0.0004

Data Index: 120318 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0166. Min Act: -0.0005

Data Index: 1264393 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0165. Min Act: -0.0004

Data Index: 73084 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0165. Min Act: -0.0004

Data Index: 58658 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0165. Min Act: -0.0005

Data Index: 214436 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0165. Min Act: -0.0004

Data Index: 989376 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0164. Min Act: -0.0004

Data Index: 1144041 (C4 (Web Text))

Max Activating Token Index: 627