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

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

Neuron 3448 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: 0.1201. Min Range: -0.1201

Max Act: 0.1195. Min Act: -0.0002

Data Index: 724756 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1201. Min Act: -0.0002

Data Index: 363523 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1176. Min Act: -0.0002

Data Index: 662617 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1149. Min Act: -0.0002

Data Index: 1057017 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1113. Min Act: -0.0002

Data Index: 815071 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1110. Min Act: -0.0002

Data Index: 368021 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1135. Min Act: -0.0002

Data Index: 1178808 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1111. Min Act: -0.0002

Data Index: 706875 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1115. Min Act: -0.0002

Data Index: 584649 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1137. Min Act: -0.0003

Data Index: 336710 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1087. Min Act: -0.0002

Data Index: 997039 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1061. Min Act: -0.0003

Data Index: 200012 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1088. Min Act: -0.0002

Data Index: 413698 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1061. Min Act: -0.0003

Data Index: 1343074 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1074. Min Act: -0.0002

Data Index: 67252 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1062. Min Act: -0.0002

Data Index: 570518 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1046. Min Act: -0.0002

Data Index: 1335598 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1063. Min Act: -0.0002

Data Index: 617454 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1050. Min Act: -0.0002

Data Index: 710481 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.1201. Min Range: -0.1201

Max Act: 0.1042. Min Act: -0.0002

Data Index: 115993 (C4 (Web Text))

Max Activating Token Index: 400