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

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

Neuron 1820 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0184. Min Act: -0.0006

Data Index: 408872 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0196. Min Act: -0.0006

Data Index: 1184374 (C4 (Web Text))

Max Activating Token Index: 565

Text #2

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0177. Min Act: -0.0006

Data Index: 504673 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0178. Min Act: -0.0006

Data Index: 897973 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0184. Min Act: -0.0006

Data Index: 158662 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0173. Min Act: -0.0006

Data Index: 843601 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0180. Min Act: -0.0006

Data Index: 998625 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0175. Min Act: -0.0006

Data Index: 834769 (C4 (Web Text))

Max Activating Token Index: 75

Text #8

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0167. Min Act: -0.0006

Data Index: 594402 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0176. Min Act: -0.0006

Data Index: 409959 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0171. Min Act: -0.0006

Data Index: 954613 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0175. Min Act: -0.0006

Data Index: 585816 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0170. Min Act: -0.0006

Data Index: 124878 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0158. Min Act: -0.0006

Data Index: 518144 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0166. Min Act: -0.0006

Data Index: 58369 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0174. Min Act: -0.0006

Data Index: 450087 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0168. Min Act: -0.0006

Data Index: 443415 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0164. Min Act: -0.0006

Data Index: 112031 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0167. Min Act: -0.0006

Data Index: 1263980 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0159. Min Act: -0.0006

Data Index: 568460 (C4 (Web Text))

Max Activating Token Index: 370