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

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

Neuron 2746 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2407. Min Act: -0.0000

Data Index: 1039972 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2197. Min Act: -0.0000

Data Index: 322182 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2048. Min Act: -0.0000

Data Index: 1110549 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.2051. Min Act: -0.0000

Data Index: 1120037 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1984. Min Act: -0.0000

Data Index: 648353 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1928. Min Act: -0.0000

Data Index: 932833 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1185670 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1874. Min Act: -0.0001

Data Index: 1252965 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1858. Min Act: -0.0001

Data Index: 155511 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1891. Min Act: -0.0000

Data Index: 369969 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1839. Min Act: -0.0000

Data Index: 817807 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1766. Min Act: -0.0001

Data Index: 858865 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1877. Min Act: -0.0001

Data Index: 631962 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1809. Min Act: -0.0000

Data Index: 854261 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1737. Min Act: -0.0000

Data Index: 263951 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1801. Min Act: -0.0000

Data Index: 266281 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1855. Min Act: -0.0001

Data Index: 310848 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1834. Min Act: -0.0001

Data Index: 1141994 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1770. Min Act: -0.0000

Data Index: 756599 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 0.2407. Min Range: -0.2407

Max Act: 0.1766. Min Act: -0.0000

Data Index: 1258700 (C4 (Web Text))

Max Activating Token Index: 150