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

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

Neuron 366 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1302. Min Act: -0.0002

Data Index: 64216 (C4 (Web Text))

Max Activating Token Index: 760

Text #1

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1226. Min Act: -0.0002

Data Index: 1066423 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1177. Min Act: -0.0002

Data Index: 1186373 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1141. Min Act: -0.0002

Data Index: 1047442 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1163. Min Act: -0.0002

Data Index: 169566 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1155. Min Act: -0.0002

Data Index: 1183437 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1068. Min Act: -0.0002

Data Index: 1295471 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1122. Min Act: -0.0002

Data Index: 887647 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1137. Min Act: 0.0000

Data Index: 812212 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1065. Min Act: -0.0001

Data Index: 881537 (C4 (Web Text))

Max Activating Token Index: 169

Text #10

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1094. Min Act: -0.0002

Data Index: 394255 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1084. Min Act: -0.0002

Data Index: 109904 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1059. Min Act: -0.0002

Data Index: 1253551 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1080. Min Act: -0.0002

Data Index: 1346649 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1027. Min Act: -0.0001

Data Index: 484759 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1079. Min Act: -0.0002

Data Index: 1006280 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1042. Min Act: -0.0002

Data Index: 1267852 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1026. Min Act: -0.0002

Data Index: 428134 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.1007. Min Act: -0.0001

Data Index: 931433 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.1302. Min Range: -0.1302

Max Act: 0.0942. Min Act: -0.0001

Data Index: 1263946 (C4 (Web Text))

Max Activating Token Index: 171