Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2567 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.1016. Min Act: -0.0002

Data Index: 841486 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.1045. Min Act: -0.0001

Data Index: 1085807 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0960. Min Act: -0.0001

Data Index: 266917 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0945. Min Act: -0.0001

Data Index: 1245557 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0910. Min Act: -0.0002

Data Index: 345992 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0960. Min Act: -0.0002

Data Index: 570542 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0895. Min Act: -0.0002

Data Index: 1137186 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0938. Min Act: -0.0002

Data Index: 350868 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0885. Min Act: -0.0002

Data Index: 735584 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0844. Min Act: -0.0001

Data Index: 931342 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0850. Min Act: -0.0001

Data Index: 53322 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0829. Min Act: -0.0002

Data Index: 1280612 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0859. Min Act: -0.0002

Data Index: 1328039 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0813. Min Act: -0.0001

Data Index: 1032738 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0840. Min Act: -0.0002

Data Index: 879562 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0797. Min Act: -0.0002

Data Index: 637795 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0793. Min Act: -0.0001

Data Index: 787107 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1017120 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0818. Min Act: -0.0002

Data Index: 242497 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0809. Min Act: -0.0002

Data Index: 498751 (C4 (Web Text))

Max Activating Token Index: 127