Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3737 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1176. Min Act: -0.0002

Data Index: 1344689 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1170. Min Act: -0.0002

Data Index: 716223 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1167. Min Act: -0.0002

Data Index: 235962 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1158. Min Act: -0.0002

Data Index: 1140144 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1156. Min Act: -0.0002

Data Index: 510811 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1154. Min Act: -0.0002

Data Index: 374873 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1132. Min Act: -0.0002

Data Index: 854623 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1129. Min Act: -0.0002

Data Index: 1187953 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1124. Min Act: -0.0002

Data Index: 1188718 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1123. Min Act: -0.0002

Data Index: 404686 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1115. Min Act: -0.0002

Data Index: 179773 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1098. Min Act: -0.0002

Data Index: 458656 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1094. Min Act: -0.0002

Data Index: 1139587 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1093. Min Act: -0.0002

Data Index: 702890 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1079. Min Act: -0.0002

Data Index: 356378 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1079. Min Act: -0.0002

Data Index: 370384 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1079. Min Act: -0.0002

Data Index: 397006 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1074. Min Act: -0.0002

Data Index: 373786 (C4 (Web Text))

Max Activating Token Index: 364

Text #18

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1060. Min Act: -0.0002

Data Index: 59481 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.1176. Min Range: -0.1176

Max Act: 0.1096. Min Act: -0.0002

Data Index: 202777 (C4 (Web Text))

Max Activating Token Index: 504