Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4547 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0967. Min Act: -0.0002

Data Index: 1144633 (C4 (Web Text))

Max Activating Token Index: 753

Text #1

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0934. Min Act: -0.0002

Data Index: 255622 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0880. Min Act: -0.0002

Data Index: 28045 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0865. Min Act: -0.0002

Data Index: 529856 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0842. Min Act: -0.0002

Data Index: 368614 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0824. Min Act: -0.0002

Data Index: 1276110 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0833. Min Act: -0.0002

Data Index: 473245 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0790. Min Act: -0.0002

Data Index: 1018624 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1154257 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0834. Min Act: -0.0002

Data Index: 1027159 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0675. Min Act: -0.0002

Data Index: 975620 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0745. Min Act: -0.0002

Data Index: 697425 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1161913 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0722. Min Act: -0.0002

Data Index: 511530 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0754. Min Act: -0.0002

Data Index: 889510 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0774. Min Act: -0.0002

Data Index: 778945 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1068924 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1170815 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0756. Min Act: -0.0002

Data Index: 654108 (C4 (Web Text))

Max Activating Token Index: 441

Text #19

Max Range: 0.0967. Min Range: -0.0967

Max Act: 0.0721. Min Act: -0.0002

Data Index: 259916 (C4 (Web Text))

Max Activating Token Index: 722