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

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

Neuron 1691 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1030. Min Act: -0.0006

Data Index: 685227 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1023. Min Act: -0.0006

Data Index: 1312349 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1019. Min Act: -0.0006

Data Index: 1210987 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1038. Min Act: -0.0006

Data Index: 1223725 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0999. Min Act: -0.0006

Data Index: 590435 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0960. Min Act: -0.0006

Data Index: 1056897 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0910. Min Act: -0.0006

Data Index: 180241 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0905. Min Act: -0.0006

Data Index: 452090 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0891. Min Act: -0.0006

Data Index: 297204 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0930. Min Act: -0.0006

Data Index: 909264 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0848. Min Act: -0.0006

Data Index: 486821 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0922. Min Act: -0.0006

Data Index: 1099111 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0985. Min Act: -0.0006

Data Index: 768504 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0907. Min Act: -0.0006

Data Index: 322813 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0870. Min Act: -0.0006

Data Index: 413576 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0900. Min Act: -0.0006

Data Index: 1181077 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0936. Min Act: -0.0006

Data Index: 14090 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0896. Min Act: -0.0006

Data Index: 479621 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0891. Min Act: -0.0006

Data Index: 1170733 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0888. Min Act: -0.0006

Data Index: 959915 (C4 (Web Text))

Max Activating Token Index: 604