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

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

Neuron 159 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: 0.1833. Min Range: -0.1833

Max Act: 0.1833. Min Act: -0.0002

Data Index: 602349 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1723. Min Act: -0.0002

Data Index: 1181713 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1245. Min Act: -0.0002

Data Index: 1037509 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1192. Min Act: -0.0002

Data Index: 273172 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1128. Min Act: -0.0002

Data Index: 801607 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1109. Min Act: -0.0002

Data Index: 526549 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1089. Min Act: -0.0002

Data Index: 521732 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1069. Min Act: -0.0002

Data Index: 311331 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1046. Min Act: -0.0002

Data Index: 190878 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1067. Min Act: -0.0002

Data Index: 951230 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1083. Min Act: -0.0002

Data Index: 1205569 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1035. Min Act: -0.0002

Data Index: 556221 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1027. Min Act: -0.0002

Data Index: 162293 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1035. Min Act: -0.0002

Data Index: 617189 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1002. Min Act: -0.0002

Data Index: 196151 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1022. Min Act: -0.0002

Data Index: 851603 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.0992. Min Act: -0.0002

Data Index: 41419 (C4 (Web Text))

Max Activating Token Index: 974

Text #17

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1010. Min Act: -0.0002

Data Index: 1100072 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.1087. Min Act: -0.0002

Data Index: 609024 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.1833. Min Range: -0.1833

Max Act: 0.0960. Min Act: -0.0002

Data Index: 967799 (C4 (Web Text))

Max Activating Token Index: 850