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

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

Neuron 4083 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0897. Min Act: -0.0000

Data Index: 675674 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0744. Min Act: -0.0000

Data Index: 647580 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0668. Min Act: -0.0000

Data Index: 1011781 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0622. Min Act: 0.0001

Data Index: 316520 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0624. Min Act: -0.0000

Data Index: 526547 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0634. Min Act: -0.0000

Data Index: 215522 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0609. Min Act: -0.0000

Data Index: 1060080 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0609. Min Act: -0.0000

Data Index: 166479 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0634. Min Act: -0.0000

Data Index: 680671 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0595. Min Act: -0.0000

Data Index: 1200487 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0592. Min Act: -0.0000

Data Index: 733768 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0562. Min Act: -0.0000

Data Index: 726837 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0577. Min Act: -0.0000

Data Index: 724629 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0601. Min Act: -0.0000

Data Index: 904786 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0600. Min Act: -0.0000

Data Index: 943429 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0549. Min Act: -0.0000

Data Index: 842764 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0545. Min Act: -0.0000

Data Index: 734760 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0590. Min Act: -0.0000

Data Index: 295793 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0614. Min Act: -0.0000

Data Index: 799658 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0547. Min Act: -0.0000

Data Index: 604521 (C4 (Web Text))

Max Activating Token Index: 817