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

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

Neuron 4805 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: 0.2654. Min Range: -0.2654

Max Act: 0.2654. Min Act: -0.0001

Data Index: 1018617 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.2654. Min Range: -0.2654

Max Act: 0.2379. Min Act: -0.0001

Data Index: 1357386 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.2654. Min Range: -0.2654

Max Act: 0.2338. Min Act: -0.0001

Data Index: 600079 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.2654. Min Range: -0.2654

Max Act: 0.2304. Min Act: -0.0001

Data Index: 137254 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.2654. Min Range: -0.2654

Max Act: 0.2237. Min Act: -0.0001

Data Index: 1171331 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.2654. Min Range: -0.2654

Max Act: 0.2246. Min Act: -0.0001

Data Index: 596576 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.2654. Min Range: -0.2654

Max Act: 0.2300. Min Act: -0.0001

Data Index: 30516 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.2654. Min Range: -0.2654

Max Act: 0.2281. Min Act: -0.0001

Data Index: 56517 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.2654. Min Range: -0.2654

Max Act: 0.2187. Min Act: -0.0001

Data Index: 702240 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 0.2654. Min Range: -0.2654

Max Act: 0.2178. Min Act: -0.0001

Data Index: 59207 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.2654. Min Range: -0.2654

Max Act: 0.2210. Min Act: -0.0001

Data Index: 119170 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.2654. Min Range: -0.2654

Max Act: 0.2178. Min Act: -0.0001

Data Index: 1183443 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 0.2654. Min Range: -0.2654

Max Act: 0.2173. Min Act: -0.0001

Data Index: 725084 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.2654. Min Range: -0.2654

Max Act: 0.2085. Min Act: -0.0001

Data Index: 418763 (C4 (Web Text))

Max Activating Token Index: 449

Text #14

Max Range: 0.2654. Min Range: -0.2654

Max Act: 0.2151. Min Act: -0.0001

Data Index: 192113 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 0.2654. Min Range: -0.2654

Max Act: 0.2058. Min Act: -0.0001

Data Index: 468690 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 0.2654. Min Range: -0.2654

Max Act: 0.2128. Min Act: -0.0001

Data Index: 1253199 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.2654. Min Range: -0.2654

Max Act: 0.2114. Min Act: -0.0001

Data Index: 977163 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.2654. Min Range: -0.2654

Max Act: 0.2111. Min Act: -0.0001

Data Index: 773345 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.2654. Min Range: -0.2654

Max Act: 0.2131. Min Act: -0.0001

Data Index: 59765 (C4 (Web Text))

Max Activating Token Index: 275