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

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

Neuron 28 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.2069. Min Act: -0.0001

Data Index: 1059502 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.2046. Min Act: -0.0001

Data Index: 595060 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1933. Min Act: -0.0001

Data Index: 862056 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1944. Min Act: -0.0001

Data Index: 285629 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1984. Min Act: -0.0001

Data Index: 187175 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1882. Min Act: -0.0001

Data Index: 713597 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1839. Min Act: -0.0001

Data Index: 165780 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1827. Min Act: -0.0001

Data Index: 602905 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1762. Min Act: -0.0001

Data Index: 1291652 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1807. Min Act: -0.0001

Data Index: 1214862 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1774. Min Act: -0.0001

Data Index: 1359007 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1782. Min Act: -0.0001

Data Index: 257894 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1958. Min Act: -0.0001

Data Index: 507364 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1895. Min Act: -0.0001

Data Index: 1015551 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1756. Min Act: -0.0001

Data Index: 76673 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1878. Min Act: -0.0001

Data Index: 998029 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1748. Min Act: -0.0001

Data Index: 635141 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1787. Min Act: -0.0001

Data Index: 1223727 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1911. Min Act: -0.0001

Data Index: 568527 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 0.2069. Min Range: -0.2069

Max Act: 0.1770. Min Act: -0.0001

Data Index: 954264 (C4 (Web Text))

Max Activating Token Index: 639