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

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

Neuron 3423 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: 0.1153. Min Range: -0.1153

Max Act: 0.1153. Min Act: -0.0001

Data Index: 1275244 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.1046. Min Act: -0.0001

Data Index: 1310298 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0931. Min Act: -0.0001

Data Index: 1333840 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0865. Min Act: -0.0001

Data Index: 922701 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0796. Min Act: -0.0001

Data Index: 444040 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0895. Min Act: -0.0001

Data Index: 126782 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0902. Min Act: -0.0001

Data Index: 435583 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0773. Min Act: -0.0001

Data Index: 508977 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1238981 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0817. Min Act: -0.0001

Data Index: 1234769 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0802. Min Act: -0.0001

Data Index: 1071614 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0818. Min Act: -0.0001

Data Index: 1230466 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0789. Min Act: -0.0001

Data Index: 784052 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0753. Min Act: -0.0001

Data Index: 1278528 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0877. Min Act: -0.0001

Data Index: 706645 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0827. Min Act: -0.0001

Data Index: 1066491 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0850. Min Act: -0.0001

Data Index: 561836 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0773. Min Act: -0.0001

Data Index: 1022533 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0733. Min Act: -0.0001

Data Index: 583412 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 0.1153. Min Range: -0.1153

Max Act: 0.0777. Min Act: -0.0001

Data Index: 518377 (C4 (Web Text))

Max Activating Token Index: 980