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

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

Neuron 5432 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.1667. Min Act: -0.0001

Data Index: 385537 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.0700. Min Act: -0.0002

Data Index: 999578 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.0012. Min Act: -0.0001

Data Index: 636145 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.0161. Min Act: -0.0001

Data Index: 990222 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9766. Min Act: -0.0001

Data Index: 347816 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 1.1667. Min Range: -1.1667

Max Act: 1.0116. Min Act: -0.0001

Data Index: 813863 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9228. Min Act: -0.0001

Data Index: 836123 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9376. Min Act: -0.0001

Data Index: 1073692 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9190. Min Act: -0.0001

Data Index: 446332 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9076. Min Act: -0.0001

Data Index: 1086179 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.9024. Min Act: -0.0001

Data Index: 1110853 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8410. Min Act: -0.0001

Data Index: 412263 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8439. Min Act: -0.0001

Data Index: 1296428 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8617. Min Act: -0.0001

Data Index: 653020 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8812. Min Act: -0.0001

Data Index: 238889 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8527. Min Act: -0.0001

Data Index: 129217 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8779. Min Act: -0.0001

Data Index: 432796 (C4 (Web Text))

Max Activating Token Index: 258

Text #17

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8247. Min Act: -0.0001

Data Index: 678940 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8390. Min Act: -0.0002

Data Index: 240118 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 1.1667. Min Range: -1.1667

Max Act: 0.8401. Min Act: -0.0001

Data Index: 845893 (C4 (Web Text))

Max Activating Token Index: 133