Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 33 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.3256. Min Act: -0.0001

Data Index: 561787 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2636. Min Act: -0.0001

Data Index: 936287 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2550. Min Act: -0.0001

Data Index: 1261637 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2321. Min Act: -0.0001

Data Index: 343103 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2300. Min Act: -0.0001

Data Index: 52303 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2297. Min Act: -0.0001

Data Index: 1335414 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2165. Min Act: -0.0001

Data Index: 1126020 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2153. Min Act: -0.0001

Data Index: 1080630 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2234. Min Act: -0.0001

Data Index: 1317475 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2157. Min Act: -0.0001

Data Index: 913037 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2224. Min Act: -0.0001

Data Index: 740031 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2118. Min Act: -0.0001

Data Index: 1177471 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2086. Min Act: -0.0001

Data Index: 636668 (C4 (Web Text))

Max Activating Token Index: 857

Text #13

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2057. Min Act: -0.0001

Data Index: 549348 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.1979. Min Act: -0.0001

Data Index: 333041 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2047. Min Act: -0.0001

Data Index: 351109 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2013. Min Act: -0.0001

Data Index: 432488 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2006. Min Act: -0.0001

Data Index: 877216 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.2008. Min Act: -0.0001

Data Index: 791030 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 0.3256. Min Range: -0.3256

Max Act: 0.1938. Min Act: -0.0001

Data Index: 1158079 (C4 (Web Text))

Max Activating Token Index: 743