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

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

Neuron 800 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: 0.0195. Min Range: -0.0195

Max Act: 0.0195. Min Act: -0.0006

Data Index: 839841 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0174. Min Act: -0.0006

Data Index: 1176181 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0177. Min Act: -0.0006

Data Index: 842722 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0172. Min Act: -0.0006

Data Index: 1303151 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0161. Min Act: -0.0006

Data Index: 1243686 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0162. Min Act: -0.0006

Data Index: 82678 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0158. Min Act: -0.0006

Data Index: 1285316 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0169. Min Act: -0.0006

Data Index: 1351949 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0154. Min Act: -0.0006

Data Index: 391929 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0162. Min Act: -0.0006

Data Index: 1099601 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0157. Min Act: -0.0006

Data Index: 595728 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1019959 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0142. Min Act: -0.0006

Data Index: 935068 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0147. Min Act: -0.0006

Data Index: 889746 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0154. Min Act: -0.0006

Data Index: 51870 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0150. Min Act: -0.0006

Data Index: 870657 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0150. Min Act: -0.0006

Data Index: 413314 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0144. Min Act: -0.0006

Data Index: 671454 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0151. Min Act: -0.0005

Data Index: 451268 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0157. Min Act: -0.0006

Data Index: 1123843 (C4 (Web Text))

Max Activating Token Index: 959