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

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

Neuron 2686 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.3018. Min Act: -0.0001

Data Index: 97418 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2201. Min Act: -0.0001

Data Index: 975285 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2230. Min Act: -0.0001

Data Index: 1539334 (Python Code)

Max Activating Token Index: 891

Text #3

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.1849. Min Act: -0.0001

Data Index: 207740 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2005. Min Act: -0.0001

Data Index: 1585717 (Python Code)

Max Activating Token Index: 506

Text #5

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.1854. Min Act: -0.0001

Data Index: 164783 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2006. Min Act: -0.0001

Data Index: 78316 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.1900. Min Act: -0.0000

Data Index: 1088126 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.1890. Min Act: -0.0001

Data Index: 1444973 (Python Code)

Max Activating Token Index: 256

Text #9

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.1473. Min Act: -0.0001

Data Index: 97971 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.1530. Min Act: -0.0001

Data Index: 464426 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.1616. Min Act: -0.0001

Data Index: 270632 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.1830. Min Act: -0.0001

Data Index: 1477995 (Python Code)

Max Activating Token Index: 937

Text #13

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.1629. Min Act: -0.0000

Data Index: 704005 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.1671. Min Act: -0.0001

Data Index: 892200 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.1415. Min Act: -0.0000

Data Index: 1282032 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.1624. Min Act: -0.0000

Data Index: 1203653 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.1425. Min Act: -0.0001

Data Index: 193926 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.1574. Min Act: -0.0000

Data Index: 1292585 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.1619. Min Act: -0.0000

Data Index: 270480 (C4 (Web Text))

Max Activating Token Index: 743