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

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

Neuron 720 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0687. Min Act: -0.0001

Data Index: 810898 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0608. Min Act: -0.0001

Data Index: 57851 (C4 (Web Text))

Max Activating Token Index: 928

Text #2

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0592. Min Act: -0.0001

Data Index: 915171 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0559. Min Act: -0.0001

Data Index: 482013 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0590. Min Act: -0.0001

Data Index: 453326 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0545. Min Act: -0.0001

Data Index: 26491 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0567. Min Act: -0.0001

Data Index: 405991 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0556. Min Act: -0.0001

Data Index: 905288 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0558. Min Act: -0.0001

Data Index: 812466 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0614. Min Act: -0.0001

Data Index: 532660 (C4 (Web Text))

Max Activating Token Index: 785

Text #10

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0559. Min Act: -0.0001

Data Index: 145905 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0562. Min Act: -0.0001

Data Index: 698280 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0530. Min Act: -0.0001

Data Index: 127802 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0543. Min Act: -0.0001

Data Index: 33738 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1228924 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0527. Min Act: -0.0001

Data Index: 30523 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0537. Min Act: -0.0001

Data Index: 865690 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0489. Min Act: -0.0001

Data Index: 6881 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0513. Min Act: -0.0001

Data Index: 33017 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 0.0687. Min Range: -0.0687

Max Act: 0.0547. Min Act: -0.0001

Data Index: 365080 (C4 (Web Text))

Max Activating Token Index: 4