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

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

Neuron 3986 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: 0.3717. Min Range: -0.3717

Max Act: 0.3717. Min Act: -0.0000

Data Index: 684771 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.2272. Min Act: -0.0000

Data Index: 226256 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.2192. Min Act: -0.0000

Data Index: 799850 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.2067. Min Act: -0.0000

Data Index: 757297 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.2218. Min Act: -0.0000

Data Index: 801725 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.1965. Min Act: -0.0000

Data Index: 495541 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1417096 (Python Code)

Max Activating Token Index: 33

Text #7

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.2011. Min Act: -0.0000

Data Index: 270046 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.2002. Min Act: -0.0000

Data Index: 200579 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.1980. Min Act: -0.0000

Data Index: 266573 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.1890. Min Act: -0.0000

Data Index: 1522903 (Python Code)

Max Activating Token Index: 574

Text #11

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.1993. Min Act: -0.0000

Data Index: 795618 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1517300 (Python Code)

Max Activating Token Index: 43

Text #13

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.1890. Min Act: -0.0000

Data Index: 1084208 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.1913. Min Act: -0.0000

Data Index: 29449 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.1882. Min Act: -0.0000

Data Index: 391530 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.1883. Min Act: -0.0000

Data Index: 896685 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.1837. Min Act: -0.0000

Data Index: 728206 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.1848. Min Act: -0.0000

Data Index: 1588657 (Python Code)

Max Activating Token Index: 149

Text #19

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.1776. Min Act: -0.0000

Data Index: 23794 (C4 (Web Text))

Max Activating Token Index: 326