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

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

Neuron 4467 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1730. Min Act: -0.0001

Data Index: 1251103 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1607. Min Act: -0.0001

Data Index: 272118 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1516. Min Act: -0.0001

Data Index: 897835 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1125. Min Act: -0.0001

Data Index: 1190509 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1307. Min Act: -0.0001

Data Index: 673125 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1228. Min Act: -0.0001

Data Index: 793713 (C4 (Web Text))

Max Activating Token Index: 513

Text #6

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1271. Min Act: -0.0001

Data Index: 767483 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1062. Min Act: -0.0001

Data Index: 611888 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1145. Min Act: -0.0001

Data Index: 31596 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1230. Min Act: -0.0001

Data Index: 715332 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1059. Min Act: -0.0001

Data Index: 388147 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1201. Min Act: -0.0001

Data Index: 561777 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1022. Min Act: -0.0001

Data Index: 874289 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1207. Min Act: -0.0001

Data Index: 196676 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1149. Min Act: -0.0001

Data Index: 1090803 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1153. Min Act: -0.0001

Data Index: 707673 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1159. Min Act: -0.0001

Data Index: 1152203 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1152. Min Act: -0.0001

Data Index: 376160 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1263. Min Act: -0.0001

Data Index: 898849 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 0.1730. Min Range: -0.1730

Max Act: 0.1084. Min Act: -0.0001

Data Index: 291831 (C4 (Web Text))

Max Activating Token Index: 592