Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1852 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0909. Min Act: -0.0001

Data Index: 1638466 (Python Code)

Max Activating Token Index: 775

Text #1

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0806. Min Act: -0.0001

Data Index: 1631415 (Python Code)

Max Activating Token Index: 272

Text #2

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0826. Min Act: -0.0000

Data Index: 110049 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0810. Min Act: -0.0000

Data Index: 1478339 (Python Code)

Max Activating Token Index: 893

Text #4

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0801. Min Act: -0.0001

Data Index: 1062973 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0742. Min Act: -0.0000

Data Index: 1540839 (Python Code)

Max Activating Token Index: 706

Text #6

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0734. Min Act: -0.0001

Data Index: 1105072 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0768. Min Act: -0.0001

Data Index: 188157 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0760. Min Act: -0.0001

Data Index: 161925 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0753. Min Act: -0.0001

Data Index: 1077441 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0735. Min Act: -0.0001

Data Index: 1126981 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0706. Min Act: -0.0001

Data Index: 1135427 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0699. Min Act: -0.0001

Data Index: 282937 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0724. Min Act: -0.0001

Data Index: 997659 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0721. Min Act: -0.0001

Data Index: 891543 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0717. Min Act: -0.0000

Data Index: 632185 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0743. Min Act: -0.0001

Data Index: 1210311 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0681. Min Act: -0.0001

Data Index: 542761 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0680. Min Act: -0.0001

Data Index: 1443994 (Python Code)

Max Activating Token Index: 992

Text #19

Max Range: 0.0909. Min Range: -0.0909

Max Act: 0.0668. Min Act: -0.0000

Data Index: 458115 (C4 (Web Text))

Max Activating Token Index: 508