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

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

Neuron 551 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1225. Min Act: -0.0005

Data Index: 184564 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1235. Min Act: -0.0005

Data Index: 1085753 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1166. Min Act: -0.0005

Data Index: 504801 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1264. Min Act: -0.0005

Data Index: 775706 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1184. Min Act: -0.0005

Data Index: 930725 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1181. Min Act: -0.0005

Data Index: 787580 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1177. Min Act: -0.0005

Data Index: 871810 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1145. Min Act: -0.0005

Data Index: 678335 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1126. Min Act: -0.0005

Data Index: 86680 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1123. Min Act: -0.0005

Data Index: 856665 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1131. Min Act: -0.0005

Data Index: 721865 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1078. Min Act: -0.0005

Data Index: 1038719 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1123. Min Act: -0.0005

Data Index: 800863 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1134. Min Act: -0.0005

Data Index: 76038 (C4 (Web Text))

Max Activating Token Index: 689

Text #14

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1140. Min Act: -0.0005

Data Index: 540992 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1094. Min Act: -0.0005

Data Index: 872071 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1115. Min Act: -0.0005

Data Index: 979901 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1095. Min Act: -0.0005

Data Index: 567090 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1074. Min Act: -0.0005

Data Index: 700206 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.1264. Min Range: -0.1264

Max Act: 0.1108. Min Act: -0.0005

Data Index: 663083 (C4 (Web Text))

Max Activating Token Index: 881