Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3655 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0756. Min Range: -1.0756

Max Act: 1.0756. Min Act: -0.0000

Data Index: 336680 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.9516. Min Act: -0.0000

Data Index: 440110 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.9521. Min Act: -0.0001

Data Index: 56645 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.9346. Min Act: -0.0001

Data Index: 679257 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.7850. Min Act: -0.0001

Data Index: 512312 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 1.0756. Min Range: -1.0756

Max Act: 1.0743. Min Act: -0.0000

Data Index: 656807 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 1.0756. Min Range: -1.0756

Max Act: 1.0549. Min Act: -0.0000

Data Index: 1240079 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.8721. Min Act: -0.0000

Data Index: 543150 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.8629. Min Act: -0.0000

Data Index: 716702 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.8332. Min Act: -0.0000

Data Index: 87499 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.8810. Min Act: -0.0000

Data Index: 881573 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.8085. Min Act: -0.0001

Data Index: 666787 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.7935. Min Act: -0.0000

Data Index: 20606 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.7901. Min Act: -0.0001

Data Index: 646827 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.7051. Min Act: -0.0000

Data Index: 258391 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.8281. Min Act: -0.0000

Data Index: 1109212 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.8072. Min Act: -0.0001

Data Index: 378571 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.7046. Min Act: -0.0000

Data Index: 602824 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.8340. Min Act: -0.0000

Data Index: 220734 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 1.0756. Min Range: -1.0756

Max Act: 0.8355. Min Act: -0.0001

Data Index: 602200 (C4 (Web Text))

Max Activating Token Index: 178