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

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

Neuron 4917 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0765. Min Act: -0.0001

Data Index: 1606220 (Python Code)

Max Activating Token Index: 683

Text #1

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0754. Min Act: -0.0001

Data Index: 562864 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0672. Min Act: -0.0001

Data Index: 1583150 (Python Code)

Max Activating Token Index: 649

Text #3

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0678. Min Act: -0.0001

Data Index: 882845 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0671. Min Act: -0.0001

Data Index: 685693 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0676. Min Act: -0.0001

Data Index: 1153511 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0602. Min Act: -0.0001

Data Index: 1157043 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0585. Min Act: -0.0001

Data Index: 91979 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0655. Min Act: -0.0001

Data Index: 1095523 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0605. Min Act: -0.0001

Data Index: 290711 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0670. Min Act: -0.0001

Data Index: 1199675 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0544. Min Act: -0.0001

Data Index: 527694 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0619. Min Act: -0.0001

Data Index: 777047 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0614. Min Act: -0.0001

Data Index: 683798 (C4 (Web Text))

Max Activating Token Index: 61

Text #14

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1417834 (Python Code)

Max Activating Token Index: 743

Text #15

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0585. Min Act: -0.0001

Data Index: 424003 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0606. Min Act: -0.0001

Data Index: 874776 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0546. Min Act: -0.0001

Data Index: 884281 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0594. Min Act: -0.0001

Data Index: 1619177 (Python Code)

Max Activating Token Index: 287

Text #19

Max Range: 0.0765. Min Range: -0.0765

Max Act: 0.0593. Min Act: -0.0001

Data Index: 1484190 (Python Code)

Max Activating Token Index: 350