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

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

Neuron 4384 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.9017. Min Act: -0.0000

Data Index: 867459 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.7903. Min Act: -0.0000

Data Index: 146921 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.7650. Min Act: -0.0000

Data Index: 1140330 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.8650. Min Act: -0.0000

Data Index: 1271215 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6528. Min Act: -0.0001

Data Index: 67456 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6537. Min Act: -0.0001

Data Index: 494071 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6708. Min Act: -0.0000

Data Index: 869498 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6663. Min Act: -0.0000

Data Index: 928203 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6401. Min Act: -0.0001

Data Index: 1068146 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6418. Min Act: -0.0001

Data Index: 615878 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6766. Min Act: -0.0001

Data Index: 887145 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.7045. Min Act: -0.0001

Data Index: 225067 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6572. Min Act: -0.0000

Data Index: 683840 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6241. Min Act: -0.0000

Data Index: 1337560 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6868. Min Act: -0.0001

Data Index: 1089583 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6433. Min Act: -0.0000

Data Index: 1993 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6424. Min Act: -0.0001

Data Index: 1186521 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6553. Min Act: -0.0000

Data Index: 1112448 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6586. Min Act: -0.0000

Data Index: 330825 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.9017. Min Range: -0.9017

Max Act: 0.6779. Min Act: -0.0001

Data Index: 334183 (C4 (Web Text))

Max Activating Token Index: 948