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

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

Neuron 310 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0987. Min Act: -0.0002

Data Index: 426015 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0834. Min Act: -0.0002

Data Index: 180773 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0749. Min Act: -0.0002

Data Index: 549080 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1520298 (Python Code)

Max Activating Token Index: 887

Text #4

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0724. Min Act: -0.0002

Data Index: 603294 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0765. Min Act: -0.0002

Data Index: 529065 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0718. Min Act: -0.0002

Data Index: 885075 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1224160 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1647089 (Python Code)

Max Activating Token Index: 674

Text #9

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0666. Min Act: -0.0002

Data Index: 563638 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0694. Min Act: -0.0002

Data Index: 944915 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0666. Min Act: -0.0002

Data Index: 1056860 (C4 (Web Text))

Max Activating Token Index: 749

Text #12

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0645. Min Act: -0.0002

Data Index: 919357 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0662. Min Act: -0.0002

Data Index: 1388406 (Python Code)

Max Activating Token Index: 960

Text #14

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0645. Min Act: -0.0002

Data Index: 1119182 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0630. Min Act: -0.0002

Data Index: 571738 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0627. Min Act: -0.0002

Data Index: 550970 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1304711 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0607. Min Act: -0.0002

Data Index: 594896 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1054233 (C4 (Web Text))

Max Activating Token Index: 894