Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2777 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2705. Min Act: -0.0001

Data Index: 1617057 (Python Code)

Max Activating Token Index: 74

Text #1

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2793. Min Act: -0.0001

Data Index: 1418698 (Python Code)

Max Activating Token Index: 350

Text #2

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2462. Min Act: -0.0001

Data Index: 1613837 (Python Code)

Max Activating Token Index: 28

Text #3

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2207. Min Act: -0.0001

Data Index: 155925 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2205. Min Act: -0.0001

Data Index: 1650369 (Python Code)

Max Activating Token Index: 86

Text #5

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2343. Min Act: -0.0001

Data Index: 1595475 (Python Code)

Max Activating Token Index: 249

Text #6

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2380. Min Act: -0.0001

Data Index: 1457860 (Python Code)

Max Activating Token Index: 288

Text #7

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2020. Min Act: -0.0000

Data Index: 712249 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2127. Min Act: -0.0001

Data Index: 833346 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2135. Min Act: -0.0001

Data Index: 1427086 (Python Code)

Max Activating Token Index: 136

Text #10

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.2030. Min Act: -0.0001

Data Index: 1374006 (Python Code)

Max Activating Token Index: 396

Text #11

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1928. Min Act: -0.0001

Data Index: 78351 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1787. Min Act: -0.0000

Data Index: 729091 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1900. Min Act: -0.0001

Data Index: 1496639 (Python Code)

Max Activating Token Index: 265

Text #14

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1914. Min Act: -0.0000

Data Index: 602358 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1776. Min Act: -0.0001

Data Index: 1635349 (Python Code)

Max Activating Token Index: 194

Text #16

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1691. Min Act: -0.0000

Data Index: 768838 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1751. Min Act: -0.0001

Data Index: 1383374 (Python Code)

Max Activating Token Index: 449

Text #18

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1806. Min Act: -0.0001

Data Index: 572358 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 0.2793. Min Range: -0.2793

Max Act: 0.1714. Min Act: -0.0001

Data Index: 1511449 (Python Code)

Max Activating Token Index: 148