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

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

Neuron 6056 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: 0.1210. Min Range: -0.1210

Max Act: 0.1210. Min Act: -0.0002

Data Index: 700288 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1153. Min Act: -0.0002

Data Index: 727641 (C4 (Web Text))

Max Activating Token Index: 334

Text #2

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1134. Min Act: -0.0002

Data Index: 132810 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1104. Min Act: -0.0002

Data Index: 516732 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1075. Min Act: -0.0002

Data Index: 1225720 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1098. Min Act: -0.0002

Data Index: 980241 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1111. Min Act: -0.0002

Data Index: 508066 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1112. Min Act: -0.0002

Data Index: 209214 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1085. Min Act: -0.0003

Data Index: 776988 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1094. Min Act: -0.0002

Data Index: 141164 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1068. Min Act: -0.0002

Data Index: 919713 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1040. Min Act: -0.0002

Data Index: 1269389 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1044. Min Act: -0.0003

Data Index: 544491 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1045. Min Act: -0.0002

Data Index: 923284 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1053. Min Act: -0.0002

Data Index: 545258 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1045. Min Act: -0.0002

Data Index: 583648 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1023. Min Act: -0.0002

Data Index: 1253103 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1021. Min Act: -0.0003

Data Index: 133923 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1064. Min Act: -0.0002

Data Index: 423200 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1039. Min Act: -0.0002

Data Index: 941077 (C4 (Web Text))

Max Activating Token Index: 145