Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 585 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3645. Min Range: -2.3645

Max Act: 2.3645. Min Act: -0.0000

Data Index: 1408840 (Python Code)

Max Activating Token Index: 49

Text #1

Max Range: 2.3645. Min Range: -2.3645

Max Act: 2.2777. Min Act: -0.0000

Data Index: 1471839 (Python Code)

Max Activating Token Index: 19

Text #2

Max Range: 2.3645. Min Range: -2.3645

Max Act: 2.2117. Min Act: -0.0000

Data Index: 875289 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 2.3645. Min Range: -2.3645

Max Act: 2.1928. Min Act: -0.0000

Data Index: 1030818 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 2.3645. Min Range: -2.3645

Max Act: 2.0728. Min Act: -0.0000

Data Index: 1254723 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 2.3645. Min Range: -2.3645

Max Act: 2.0615. Min Act: -0.0000

Data Index: 433615 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 2.3645. Min Range: -2.3645

Max Act: 2.1035. Min Act: -0.0000

Data Index: 1451100 (Python Code)

Max Activating Token Index: 279

Text #7

Max Range: 2.3645. Min Range: -2.3645

Max Act: 2.1900. Min Act: -0.0000

Data Index: 278514 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 2.3645. Min Range: -2.3645

Max Act: 2.0680. Min Act: -0.0000

Data Index: 177251 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 2.3645. Min Range: -2.3645

Max Act: 2.0489. Min Act: -0.0000

Data Index: 490401 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 2.3645. Min Range: -2.3645

Max Act: 2.0175. Min Act: -0.0000

Data Index: 1496673 (Python Code)

Max Activating Token Index: 546

Text #11

Max Range: 2.3645. Min Range: -2.3645

Max Act: 1.8900. Min Act: -0.0000

Data Index: 432447 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 2.3645. Min Range: -2.3645

Max Act: 1.9902. Min Act: -0.0000

Data Index: 1443975 (Python Code)

Max Activating Token Index: 33

Text #13

Max Range: 2.3645. Min Range: -2.3645

Max Act: 1.9860. Min Act: -0.0000

Data Index: 378408 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 2.3645. Min Range: -2.3645

Max Act: 1.9831. Min Act: -0.0000

Data Index: 860283 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 2.3645. Min Range: -2.3645

Max Act: 1.9630. Min Act: -0.0000

Data Index: 45930 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 2.3645. Min Range: -2.3645

Max Act: 2.0564. Min Act: -0.0000

Data Index: 609563 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 2.3645. Min Range: -2.3645

Max Act: 2.0624. Min Act: -0.0000

Data Index: 55729 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 2.3645. Min Range: -2.3645

Max Act: 1.8914. Min Act: -0.0000

Data Index: 123127 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 2.3645. Min Range: -2.3645

Max Act: 1.8906. Min Act: -0.0000

Data Index: 1363926 (Python Code)

Max Activating Token Index: 9