Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 240 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.2205. Min Act: -0.0004

Data Index: 445285 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1892. Min Act: -0.0004

Data Index: 556018 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1998. Min Act: -0.0004

Data Index: 76697 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1836. Min Act: -0.0004

Data Index: 773624 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1823. Min Act: -0.0004

Data Index: 1153529 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1820. Min Act: -0.0004

Data Index: 4102 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1669. Min Act: -0.0004

Data Index: 932577 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1745. Min Act: -0.0004

Data Index: 773289 (C4 (Web Text))

Max Activating Token Index: 854

Text #8

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1749. Min Act: -0.0004

Data Index: 977015 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1721. Min Act: -0.0004

Data Index: 721263 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1703. Min Act: -0.0004

Data Index: 578262 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1698. Min Act: -0.0004

Data Index: 942045 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1575. Min Act: -0.0004

Data Index: 155924 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1706. Min Act: -0.0004

Data Index: 823246 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1696. Min Act: -0.0004

Data Index: 84393 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1693. Min Act: -0.0004

Data Index: 415930 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1545. Min Act: -0.0004

Data Index: 880095 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1666. Min Act: -0.0004

Data Index: 135678 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1583. Min Act: -0.0004

Data Index: 190652 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.2205. Min Range: -0.2205

Max Act: 0.1571. Min Act: -0.0004

Data Index: 805110 (C4 (Web Text))

Max Activating Token Index: 51