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

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

Neuron 1122 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.6249. Min Act: 0.0000

Data Index: 335011 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.6022. Min Act: -0.0000

Data Index: 996599 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5100. Min Act: -0.0000

Data Index: 1156064 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4852. Min Act: 0.0000

Data Index: 293993 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5344. Min Act: -0.0000

Data Index: 745518 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4988. Min Act: -0.0000

Data Index: 1324452 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1166224 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5143. Min Act: -0.0000

Data Index: 483703 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4625. Min Act: -0.0000

Data Index: 434928 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4666. Min Act: -0.0000

Data Index: 6010 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4576. Min Act: -0.0000

Data Index: 205547 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4516. Min Act: -0.0000

Data Index: 1070939 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4114. Min Act: -0.0000

Data Index: 601575 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4271. Min Act: 0.0001

Data Index: 693052 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4246. Min Act: -0.0000

Data Index: 181285 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1118791 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4264. Min Act: -0.0000

Data Index: 317696 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4108. Min Act: -0.0000

Data Index: 78220 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.3936. Min Act: -0.0000

Data Index: 1159146 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.3836. Min Act: -0.0000

Data Index: 205177 (C4 (Web Text))

Max Activating Token Index: 585