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

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

Neuron 1069 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: 0.1305. Min Range: -0.1305

Max Act: 0.1305. Min Act: -0.0002

Data Index: 1266467 (C4 (Web Text))

Max Activating Token Index: 839

Text #1

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1247. Min Act: -0.0002

Data Index: 245618 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1247. Min Act: -0.0002

Data Index: 1236983 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1181. Min Act: -0.0002

Data Index: 932436 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1228. Min Act: -0.0002

Data Index: 530613 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1102. Min Act: -0.0002

Data Index: 602334 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1144. Min Act: -0.0002

Data Index: 510264 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1111. Min Act: -0.0002

Data Index: 789932 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1078. Min Act: -0.0002

Data Index: 356786 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1078. Min Act: -0.0002

Data Index: 382705 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1072. Min Act: -0.0002

Data Index: 1064040 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1057. Min Act: -0.0002

Data Index: 1139763 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1019. Min Act: -0.0002

Data Index: 755803 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1013. Min Act: -0.0002

Data Index: 123261 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1013. Min Act: -0.0002

Data Index: 1175255 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1002. Min Act: -0.0002

Data Index: 4786 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0986. Min Act: -0.0002

Data Index: 1259273 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0996. Min Act: -0.0002

Data Index: 1006298 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0939. Min Act: -0.0002

Data Index: 1239243 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0974. Min Act: -0.0002

Data Index: 760285 (C4 (Web Text))

Max Activating Token Index: 545