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

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

Neuron 2506 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2628. Min Act: -0.0000

Data Index: 750499 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2390. Min Act: -0.0000

Data Index: 479311 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2337. Min Act: -0.0000

Data Index: 238770 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2425. Min Act: -0.0000

Data Index: 351167 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2210. Min Act: -0.0000

Data Index: 770642 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1067469 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2338. Min Act: -0.0000

Data Index: 806033 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2263. Min Act: -0.0000

Data Index: 925234 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2317. Min Act: -0.0000

Data Index: 987252 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2077. Min Act: -0.0000

Data Index: 764905 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2129. Min Act: -0.0000

Data Index: 214289 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2255. Min Act: -0.0000

Data Index: 997124 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2168. Min Act: -0.0000

Data Index: 859389 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1010858 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2387. Min Act: -0.0000

Data Index: 777002 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2151. Min Act: -0.0000

Data Index: 355027 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2131. Min Act: -0.0000

Data Index: 122589 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2063. Min Act: -0.0000

Data Index: 979112 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2177. Min Act: -0.0000

Data Index: 120500 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2083. Min Act: -0.0000

Data Index: 105777 (C4 (Web Text))

Max Activating Token Index: 784