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

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

Neuron 1598 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1363. Min Act: -0.0001

Data Index: 687743 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1074. Min Act: -0.0001

Data Index: 303373 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1061. Min Act: -0.0000

Data Index: 1051723 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1270003 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0976. Min Act: -0.0001

Data Index: 478450 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0905. Min Act: -0.0000

Data Index: 956556 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0913. Min Act: -0.0000

Data Index: 646920 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0831. Min Act: -0.0000

Data Index: 987541 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0827. Min Act: -0.0001

Data Index: 660601 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0841. Min Act: -0.0000

Data Index: 1251114 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0839. Min Act: -0.0000

Data Index: 940609 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0772. Min Act: -0.0001

Data Index: 853185 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0784. Min Act: -0.0000

Data Index: 619425 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0749. Min Act: -0.0000

Data Index: 475781 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0695. Min Act: -0.0000

Data Index: 966623 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0810. Min Act: -0.0000

Data Index: 1259986 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0756. Min Act: -0.0001

Data Index: 565241 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0754. Min Act: -0.0000

Data Index: 135259 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0769. Min Act: -0.0000

Data Index: 418289 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0741. Min Act: -0.0000

Data Index: 989655 (C4 (Web Text))

Max Activating Token Index: 630