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

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

Neuron 2237 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0796. Min Act: -0.0000

Data Index: 61797 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0825. Min Act: -0.0001

Data Index: 955776 (C4 (Web Text))

Max Activating Token Index: 940

Text #2

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0741. Min Act: -0.0000

Data Index: 403842 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1360607 (Python Code)

Max Activating Token Index: 1015

Text #4

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0660. Min Act: -0.0001

Data Index: 257002 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0619. Min Act: -0.0001

Data Index: 1639545 (Python Code)

Max Activating Token Index: 845

Text #6

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0629. Min Act: -0.0000

Data Index: 1158800 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0558. Min Act: -0.0001

Data Index: 1390542 (Python Code)

Max Activating Token Index: 749

Text #8

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0607. Min Act: -0.0000

Data Index: 1101114 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0631. Min Act: -0.0001

Data Index: 1023981 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0607. Min Act: -0.0001

Data Index: 408863 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1533648 (Python Code)

Max Activating Token Index: 405

Text #12

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0551. Min Act: -0.0001

Data Index: 183282 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0571. Min Act: -0.0001

Data Index: 1209497 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0607. Min Act: -0.0000

Data Index: 1303187 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0531. Min Act: -0.0000

Data Index: 734808 (C4 (Web Text))

Max Activating Token Index: 386

Text #16

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0578. Min Act: -0.0001

Data Index: 611039 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0523. Min Act: -0.0001

Data Index: 605443 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0529. Min Act: -0.0001

Data Index: 1547945 (Python Code)

Max Activating Token Index: 788

Text #19

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1602955 (Python Code)

Max Activating Token Index: 686