Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5762 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1242. Min Act: -0.0002

Data Index: 419021 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1244. Min Act: -0.0002

Data Index: 311150 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1265. Min Act: -0.0002

Data Index: 370133 (C4 (Web Text))

Max Activating Token Index: 316

Text #3

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1178. Min Act: -0.0002

Data Index: 968684 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1205. Min Act: -0.0002

Data Index: 1079010 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1183. Min Act: -0.0002

Data Index: 1199106 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1175. Min Act: -0.0002

Data Index: 401317 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1189. Min Act: -0.0002

Data Index: 27655 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1122. Min Act: -0.0002

Data Index: 1052795 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1153. Min Act: -0.0003

Data Index: 1094852 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1125. Min Act: -0.0002

Data Index: 597055 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1149. Min Act: -0.0003

Data Index: 189800 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1152. Min Act: -0.0002

Data Index: 641166 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1145. Min Act: -0.0002

Data Index: 800386 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1096. Min Act: -0.0002

Data Index: 1266914 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1094. Min Act: -0.0002

Data Index: 34005 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1114. Min Act: -0.0003

Data Index: 937224 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1106. Min Act: -0.0002

Data Index: 1239499 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1114. Min Act: -0.0002

Data Index: 527358 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1069. Min Act: -0.0002

Data Index: 1223509 (C4 (Web Text))

Max Activating Token Index: 253