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

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

Neuron 1786 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2453. Min Act: -0.0000

Data Index: 359510 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2268. Min Act: -0.0000

Data Index: 1123321 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2386. Min Act: -0.0000

Data Index: 456710 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2201. Min Act: -0.0000

Data Index: 1222932 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2116. Min Act: -0.0000

Data Index: 89531 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1147614 (C4 (Web Text))

Max Activating Token Index: 872

Text #6

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2147. Min Act: -0.0000

Data Index: 805294 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2312. Min Act: -0.0000

Data Index: 100349 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1156712 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2073. Min Act: -0.0000

Data Index: 801311 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2109. Min Act: -0.0000

Data Index: 726258 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2038. Min Act: -0.0000

Data Index: 948816 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2160. Min Act: -0.0000

Data Index: 645155 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2008. Min Act: -0.0000

Data Index: 783072 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2014. Min Act: -0.0001

Data Index: 1468066 (Python Code)

Max Activating Token Index: 133

Text #15

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2080. Min Act: -0.0000

Data Index: 1192347 (C4 (Web Text))

Max Activating Token Index: 172

Text #16

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2013. Min Act: -0.0001

Data Index: 1379909 (Python Code)

Max Activating Token Index: 358

Text #17

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2016. Min Act: -0.0000

Data Index: 63279 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.2005. Min Act: -0.0000

Data Index: 316962 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.2453. Min Range: -0.2453

Max Act: 0.1998. Min Act: -0.0000

Data Index: 435015 (C4 (Web Text))

Max Activating Token Index: 222