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

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

Neuron 4874 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: 0.2694. Min Range: -0.2694

Max Act: 0.2694. Min Act: -0.0000

Data Index: 890034 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2427. Min Act: -0.0001

Data Index: 36678 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2220. Min Act: -0.0001

Data Index: 1223726 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2391. Min Act: -0.0000

Data Index: 816795 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2212. Min Act: -0.0000

Data Index: 920098 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1298660 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2154. Min Act: -0.0000

Data Index: 1224838 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2041. Min Act: -0.0000

Data Index: 697570 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2092. Min Act: -0.0000

Data Index: 542468 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1899. Min Act: -0.0000

Data Index: 1329531 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2040. Min Act: -0.0000

Data Index: 285513 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2044. Min Act: -0.0000

Data Index: 1299591 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2029. Min Act: -0.0000

Data Index: 346108 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1947. Min Act: -0.0000

Data Index: 1184352 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2079. Min Act: -0.0000

Data Index: 1177683 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1917. Min Act: -0.0000

Data Index: 688078 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1969. Min Act: -0.0000

Data Index: 106896 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1940. Min Act: -0.0001

Data Index: 1322867 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.1874. Min Act: -0.0001

Data Index: 894794 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 0.2694. Min Range: -0.2694

Max Act: 0.2021. Min Act: -0.0000

Data Index: 898682 (C4 (Web Text))

Max Activating Token Index: 344