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

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

Neuron 3486 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0750. Min Act: -0.0001

Data Index: 714765 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0638. Min Act: -0.0001

Data Index: 1091869 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0642. Min Act: -0.0001

Data Index: 368623 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0615. Min Act: -0.0002

Data Index: 96282 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0592. Min Act: -0.0002

Data Index: 877468 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0639. Min Act: -0.0002

Data Index: 311201 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0643. Min Act: -0.0002

Data Index: 361133 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1637047 (Python Code)

Max Activating Token Index: 881

Text #8

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1542975 (Python Code)

Max Activating Token Index: 132

Text #9

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0599. Min Act: -0.0002

Data Index: 970587 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1315490 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0593. Min Act: -0.0001

Data Index: 1184868 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1370111 (Python Code)

Max Activating Token Index: 482

Text #13

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1004926 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0591. Min Act: -0.0002

Data Index: 815225 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0606. Min Act: -0.0001

Data Index: 823595 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0542. Min Act: -0.0001

Data Index: 463739 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1437147 (Python Code)

Max Activating Token Index: 1012

Text #18

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0580. Min Act: -0.0002

Data Index: 478660 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0625. Min Act: -0.0002

Data Index: 228774 (C4 (Web Text))

Max Activating Token Index: 840