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

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

Neuron 1427 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: 0.0995. Min Range: -0.0995

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1186841 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0995. Min Act: -0.0002

Data Index: 478212 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0861. Min Act: -0.0001

Data Index: 768822 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0904. Min Act: -0.0001

Data Index: 33512 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0843. Min Act: -0.0002

Data Index: 35231 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0842. Min Act: -0.0002

Data Index: 1062959 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0869. Min Act: -0.0001

Data Index: 1077892 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0878. Min Act: -0.0001

Data Index: 740605 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0817. Min Act: -0.0001

Data Index: 820698 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0758. Min Act: -0.0001

Data Index: 860532 (C4 (Web Text))

Max Activating Token Index: 362

Text #10

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0793. Min Act: -0.0002

Data Index: 640680 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0798. Min Act: -0.0002

Data Index: 582614 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0791. Min Act: -0.0002

Data Index: 872007 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0653. Min Act: -0.0001

Data Index: 583394 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0781. Min Act: -0.0002

Data Index: 102638 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0746. Min Act: -0.0002

Data Index: 793457 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1125006 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0825. Min Act: -0.0002

Data Index: 455172 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1313506 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0728. Min Act: -0.0002

Data Index: 42013 (C4 (Web Text))

Max Activating Token Index: 295