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

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

Neuron 3662 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1238. Min Act: -0.0000

Data Index: 1379366 (Python Code)

Max Activating Token Index: 938

Text #1

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1351612 (C4 (Web Text))

Max Activating Token Index: 552

Text #2

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0947. Min Act: -0.0000

Data Index: 20715 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1156. Min Act: -0.0000

Data Index: 414286 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.1008. Min Act: -0.0000

Data Index: 548322 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0923. Min Act: -0.0000

Data Index: 66557 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0858. Min Act: -0.0000

Data Index: 1632233 (Python Code)

Max Activating Token Index: 1015

Text #7

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0877. Min Act: -0.0000

Data Index: 940843 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0894. Min Act: -0.0000

Data Index: 1604261 (Python Code)

Max Activating Token Index: 986

Text #9

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0888. Min Act: -0.0000

Data Index: 454950 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0828. Min Act: -0.0000

Data Index: 605762 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0922. Min Act: -0.0000

Data Index: 939351 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0942. Min Act: -0.0000

Data Index: 6759 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0921. Min Act: -0.0000

Data Index: 1366393 (Python Code)

Max Activating Token Index: 906

Text #14

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0737. Min Act: -0.0000

Data Index: 996826 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0963. Min Act: -0.0000

Data Index: 961150 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0820. Min Act: -0.0000

Data Index: 1338550 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1012918 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0844. Min Act: -0.0000

Data Index: 840380 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.1238. Min Range: -0.1238

Max Act: 0.0844. Min Act: -0.0000

Data Index: 775067 (C4 (Web Text))

Max Activating Token Index: 745