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

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

Neuron 3212 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: 0.2274. Min Range: -0.2274

Max Act: 0.2119. Min Act: -0.0001

Data Index: 392067 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.2274. Min Range: -0.2274

Max Act: 0.2134. Min Act: -0.0001

Data Index: 1066519 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 0.2274. Min Range: -0.2274

Max Act: 0.2267. Min Act: -0.0001

Data Index: 972122 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.2274. Min Range: -0.2274

Max Act: 0.2215. Min Act: -0.0001

Data Index: 902045 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.2274. Min Range: -0.2274

Max Act: 0.2218. Min Act: -0.0001

Data Index: 1357372 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 0.2274. Min Range: -0.2274

Max Act: 0.2200. Min Act: -0.0001

Data Index: 1094274 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.2274. Min Range: -0.2274

Max Act: 0.2220. Min Act: -0.0001

Data Index: 522838 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.2274. Min Range: -0.2274

Max Act: 0.2190. Min Act: -0.0000

Data Index: 1201703 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 0.2274. Min Range: -0.2274

Max Act: 0.2035. Min Act: -0.0001

Data Index: 422529 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.2274. Min Range: -0.2274

Max Act: 0.2274. Min Act: -0.0001

Data Index: 207868 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 0.2274. Min Range: -0.2274

Max Act: 0.2014. Min Act: -0.0001

Data Index: 402379 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 0.2274. Min Range: -0.2274

Max Act: 0.2215. Min Act: -0.0001

Data Index: 352142 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.2274. Min Range: -0.2274

Max Act: 0.2142. Min Act: -0.0001

Data Index: 550865 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.2274. Min Range: -0.2274

Max Act: 0.2102. Min Act: -0.0001

Data Index: 366846 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.2274. Min Range: -0.2274

Max Act: 0.2026. Min Act: -0.0000

Data Index: 673076 (C4 (Web Text))

Max Activating Token Index: 167

Text #15

Max Range: 0.2274. Min Range: -0.2274

Max Act: 0.1959. Min Act: -0.0001

Data Index: 1093527 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 0.2274. Min Range: -0.2274

Max Act: 0.2246. Min Act: -0.0001

Data Index: 343115 (C4 (Web Text))

Max Activating Token Index: 907

Text #17

Max Range: 0.2274. Min Range: -0.2274

Max Act: 0.1995. Min Act: -0.0001

Data Index: 97176 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 0.2274. Min Range: -0.2274

Max Act: 0.2156. Min Act: -0.0001

Data Index: 232797 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 0.2274. Min Range: -0.2274

Max Act: 0.1947. Min Act: -0.0001

Data Index: 515260 (C4 (Web Text))

Max Activating Token Index: 717