Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 539 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0954. Min Act: -0.0004

Data Index: 89515 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0942. Min Act: -0.0004

Data Index: 241168 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0971. Min Act: -0.0004

Data Index: 397575 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0970. Min Act: -0.0004

Data Index: 126499 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0968. Min Act: -0.0004

Data Index: 932346 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0958. Min Act: -0.0004

Data Index: 480345 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0807. Min Act: -0.0004

Data Index: 118190 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0931. Min Act: -0.0004

Data Index: 1037239 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0877. Min Act: -0.0004

Data Index: 552675 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0853. Min Act: -0.0004

Data Index: 955698 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0814. Min Act: -0.0004

Data Index: 1213204 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0869. Min Act: -0.0004

Data Index: 1217743 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0867. Min Act: -0.0004

Data Index: 902050 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0895. Min Act: -0.0004

Data Index: 821130 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0863. Min Act: -0.0004

Data Index: 1245187 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0860. Min Act: -0.0004

Data Index: 438976 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0795. Min Act: -0.0004

Data Index: 1337600 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0823. Min Act: -0.0004

Data Index: 1199523 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0737. Min Act: -0.0004

Data Index: 520612 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 0.0971. Min Range: -0.0971

Max Act: 0.0886. Min Act: -0.0004

Data Index: 22177 (C4 (Web Text))

Max Activating Token Index: 965