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

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

Neuron 1943 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2992. Min Act: -0.0002

Data Index: 903477 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2701. Min Act: -0.0002

Data Index: 676675 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2536. Min Act: -0.0002

Data Index: 703245 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2583. Min Act: -0.0002

Data Index: 1304964 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2367. Min Act: -0.0002

Data Index: 597850 (C4 (Web Text))

Max Activating Token Index: 303

Text #5

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2156. Min Act: -0.0002

Data Index: 237826 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2323. Min Act: -0.0002

Data Index: 775514 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2286. Min Act: -0.0002

Data Index: 456679 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2331. Min Act: -0.0002

Data Index: 1115697 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2220. Min Act: -0.0002

Data Index: 966195 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2264. Min Act: -0.0002

Data Index: 938732 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2184. Min Act: -0.0002

Data Index: 931212 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2171. Min Act: -0.0002

Data Index: 1229793 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2164. Min Act: -0.0002

Data Index: 143378 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2306. Min Act: -0.0002

Data Index: 624881 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2244. Min Act: -0.0002

Data Index: 957374 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2222. Min Act: -0.0002

Data Index: 1105662 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.1842. Min Act: -0.0002

Data Index: 521826 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2124. Min Act: -0.0002

Data Index: 1195055 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.2992. Min Range: -0.2992

Max Act: 0.2130. Min Act: -0.0002

Data Index: 1104811 (C4 (Web Text))

Max Activating Token Index: 178