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

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

Neuron 1051 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.2255. Min Act: -0.0001

Data Index: 124509 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.2058. Min Act: -0.0001

Data Index: 339088 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.2054. Min Act: -0.0001

Data Index: 601719 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.2115. Min Act: -0.0001

Data Index: 1031033 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.2028. Min Act: -0.0001

Data Index: 566015 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1970. Min Act: -0.0001

Data Index: 576430 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1960. Min Act: -0.0001

Data Index: 959638 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.2026. Min Act: -0.0001

Data Index: 281541 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1880. Min Act: -0.0001

Data Index: 6680 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.2009. Min Act: -0.0001

Data Index: 161500 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.2009. Min Act: -0.0001

Data Index: 1092759 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1985. Min Act: -0.0001

Data Index: 489405 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1847. Min Act: -0.0001

Data Index: 89653 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1885. Min Act: -0.0001

Data Index: 1217088 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1881. Min Act: -0.0001

Data Index: 457470 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1940. Min Act: -0.0001

Data Index: 720690 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1928. Min Act: -0.0001

Data Index: 1151828 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1753. Min Act: -0.0001

Data Index: 803866 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1942. Min Act: -0.0001

Data Index: 1123713 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 0.2255. Min Range: -0.2255

Max Act: 0.1690. Min Act: -0.0001

Data Index: 1345012 (C4 (Web Text))

Max Activating Token Index: 216