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

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

Neuron 2808 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.7904. Min Act: -0.0001

Data Index: 212142 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6277. Min Act: -0.0001

Data Index: 792859 (C4 (Web Text))

Max Activating Token Index: 425

Text #2

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.6199. Min Act: -0.0001

Data Index: 510815 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.5823. Min Act: -0.0001

Data Index: 998212 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1047361 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.5459. Min Act: -0.0001

Data Index: 1572668 (Python Code)

Max Activating Token Index: 791

Text #6

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.5404. Min Act: -0.0001

Data Index: 419611 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.5447. Min Act: -0.0001

Data Index: 938718 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.5302. Min Act: -0.0001

Data Index: 723578 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.5250. Min Act: -0.0001

Data Index: 733361 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.5033. Min Act: -0.0001

Data Index: 468657 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.4840. Min Act: -0.0001

Data Index: 1417180 (Python Code)

Max Activating Token Index: 469

Text #12

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.4941. Min Act: -0.0000

Data Index: 362798 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.5007. Min Act: -0.0001

Data Index: 1264614 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.4965. Min Act: -0.0000

Data Index: 614519 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.4827. Min Act: -0.0000

Data Index: 671849 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.4796. Min Act: -0.0001

Data Index: 1562856 (Python Code)

Max Activating Token Index: 300

Text #17

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.4889. Min Act: -0.0000

Data Index: 682229 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.4736. Min Act: -0.0000

Data Index: 370055 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.7904. Min Range: -0.7904

Max Act: 0.4745. Min Act: -0.0001

Data Index: 466805 (C4 (Web Text))

Max Activating Token Index: 641