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

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

Neuron 2931 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: 0.0839. Min Range: -0.0839

Max Act: 0.0796. Min Act: -0.0002

Data Index: 984162 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0839. Min Act: -0.0002

Data Index: 7650 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0776. Min Act: -0.0002

Data Index: 608914 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0753. Min Act: -0.0002

Data Index: 379965 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0756. Min Act: -0.0001

Data Index: 800737 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0727. Min Act: -0.0002

Data Index: 314159 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0700. Min Act: -0.0002

Data Index: 1051358 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0768. Min Act: -0.0002

Data Index: 273027 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0771. Min Act: -0.0001

Data Index: 591420 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0745. Min Act: -0.0002

Data Index: 848826 (C4 (Web Text))

Max Activating Token Index: 988

Text #10

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0690. Min Act: -0.0002

Data Index: 1074218 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0749. Min Act: -0.0001

Data Index: 1162945 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0801. Min Act: -0.0001

Data Index: 147985 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0749. Min Act: -0.0002

Data Index: 789095 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0705. Min Act: -0.0001

Data Index: 309788 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0703. Min Act: -0.0001

Data Index: 810267 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0684. Min Act: -0.0002

Data Index: 772172 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0725. Min Act: -0.0002

Data Index: 1337172 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0690. Min Act: -0.0001

Data Index: 1328142 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0739. Min Act: -0.0002

Data Index: 723902 (C4 (Web Text))

Max Activating Token Index: 454