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

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

Neuron 3788 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2297. Min Range: -1.2297

Max Act: 1.2297. Min Act: -0.0000

Data Index: 1096758 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 1.2297. Min Range: -1.2297

Max Act: 1.0967. Min Act: -0.0000

Data Index: 596218 (C4 (Web Text))

Max Activating Token Index: 413

Text #2

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.9381. Min Act: -0.0000

Data Index: 401097 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.8528. Min Act: -0.0000

Data Index: 1317527 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.8537. Min Act: -0.0000

Data Index: 306152 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.8440. Min Act: -0.0000

Data Index: 802091 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.7690. Min Act: -0.0000

Data Index: 632763 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.8220. Min Act: -0.0000

Data Index: 1141675 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.7052. Min Act: -0.0000

Data Index: 368385 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.7710. Min Act: -0.0000

Data Index: 442447 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.7012. Min Act: -0.0000

Data Index: 178806 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.7342. Min Act: -0.0000

Data Index: 291627 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.7428. Min Act: -0.0000

Data Index: 800851 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.7871. Min Act: -0.0000

Data Index: 154660 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.7529. Min Act: -0.0000

Data Index: 1056265 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1322205 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.7289. Min Act: -0.0000

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1244865 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.7257. Min Act: -0.0000

Data Index: 1125163 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 1.2297. Min Range: -1.2297

Max Act: 0.6919. Min Act: -0.0000

Data Index: 925916 (C4 (Web Text))

Max Activating Token Index: 581