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

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

Neuron 3368 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2388. Min Act: -0.0000

Data Index: 924412 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2215. Min Act: -0.0001

Data Index: 54165 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2383. Min Act: -0.0000

Data Index: 138138 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2183. Min Act: -0.0001

Data Index: 928536 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2421. Min Act: -0.0001

Data Index: 189752 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2160. Min Act: -0.0001

Data Index: 194051 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2119. Min Act: -0.0001

Data Index: 744509 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.1970. Min Act: -0.0001

Data Index: 97176 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2002. Min Act: -0.0001

Data Index: 366846 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2063. Min Act: -0.0000

Data Index: 1133970 (C4 (Web Text))

Max Activating Token Index: 489

Text #10

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2134. Min Act: -0.0000

Data Index: 539798 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.1999. Min Act: -0.0001

Data Index: 551359 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2014. Min Act: -0.0000

Data Index: 558400 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2008. Min Act: -0.0000

Data Index: 528075 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2042. Min Act: -0.0000

Data Index: 840603 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.1875. Min Act: -0.0001

Data Index: 515260 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.1942. Min Act: -0.0001

Data Index: 714264 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.2031. Min Act: -0.0000

Data Index: 907263 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.1996. Min Act: -0.0000

Data Index: 885536 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 0.2421. Min Range: -0.2421

Max Act: 0.1847. Min Act: -0.0001

Data Index: 207868 (C4 (Web Text))

Max Activating Token Index: 905