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

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

Neuron 52 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0189. Min Act: -0.0005

Data Index: 1118678 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0182. Min Act: -0.0005

Data Index: 933318 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1002985 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0174. Min Act: -0.0005

Data Index: 1268931 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0172. Min Act: -0.0005

Data Index: 984271 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0171. Min Act: -0.0005

Data Index: 1100170 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0170. Min Act: -0.0006

Data Index: 535726 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0165. Min Act: -0.0005

Data Index: 628671 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0163. Min Act: -0.0005

Data Index: 369932 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0163. Min Act: -0.0005

Data Index: 423037 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0162. Min Act: -0.0005

Data Index: 1014913 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0164. Min Act: -0.0006

Data Index: 640274 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0161. Min Act: -0.0005

Data Index: 1155438 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0163. Min Act: -0.0005

Data Index: 528666 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0159. Min Act: -0.0005

Data Index: 295801 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0159. Min Act: -0.0005

Data Index: 1045752 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0158. Min Act: -0.0005

Data Index: 838729 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0159. Min Act: -0.0005

Data Index: 856171 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0158. Min Act: -0.0006

Data Index: 683900 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.0189. Min Range: -0.0189

Max Act: 0.0158. Min Act: -0.0005

Data Index: 775502 (C4 (Web Text))

Max Activating Token Index: 1023