Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 525 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2898. Min Range: -0.2898

Max Act: 0.2898. Min Act: -0.0000

Data Index: 517515 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 0.2898. Min Range: -0.2898

Max Act: 0.2839. Min Act: -0.0000

Data Index: 1206525 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.2898. Min Range: -0.2898

Max Act: 0.2655. Min Act: -0.0000

Data Index: 365293 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.2898. Min Range: -0.2898

Max Act: 0.2117. Min Act: -0.0000

Data Index: 15160 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.2898. Min Range: -0.2898

Max Act: 0.2221. Min Act: -0.0000

Data Index: 1039960 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 0.2898. Min Range: -0.2898

Max Act: 0.2420. Min Act: -0.0001

Data Index: 1112087 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.2898. Min Range: -0.2898

Max Act: 0.2554. Min Act: -0.0000

Data Index: 54402 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.2898. Min Range: -0.2898

Max Act: 0.2142. Min Act: -0.0000

Data Index: 212803 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 0.2898. Min Range: -0.2898

Max Act: 0.2387. Min Act: -0.0000

Data Index: 280743 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.2898. Min Range: -0.2898

Max Act: 0.2351. Min Act: -0.0000

Data Index: 359764 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 0.2898. Min Range: -0.2898

Max Act: 0.2274. Min Act: -0.0000

Data Index: 421305 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.2898. Min Range: -0.2898

Max Act: 0.2329. Min Act: -0.0000

Data Index: 217849 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.2898. Min Range: -0.2898

Max Act: 0.2272. Min Act: -0.0000

Data Index: 597111 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.2898. Min Range: -0.2898

Max Act: 0.2191. Min Act: -0.0000

Data Index: 797586 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 0.2898. Min Range: -0.2898

Max Act: 0.2021. Min Act: -0.0001

Data Index: 1350500 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.2898. Min Range: -0.2898

Max Act: 0.2076. Min Act: -0.0000

Data Index: 1323041 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 0.2898. Min Range: -0.2898

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1339174 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.2898. Min Range: -0.2898

Max Act: 0.2004. Min Act: -0.0000

Data Index: 1049841 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.2898. Min Range: -0.2898

Max Act: 0.1966. Min Act: -0.0000

Data Index: 131838 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 0.2898. Min Range: -0.2898

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1061848 (C4 (Web Text))

Max Activating Token Index: 520