Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4695 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0712. Min Act: -0.0000

Data Index: 237549 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0738. Min Act: -0.0000

Data Index: 5028 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0655. Min Act: -0.0001

Data Index: 337015 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0650. Min Act: -0.0000

Data Index: 614811 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0642. Min Act: -0.0001

Data Index: 1620929 (Python Code)

Max Activating Token Index: 153

Text #5

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0606. Min Act: -0.0000

Data Index: 853748 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0574. Min Act: -0.0001

Data Index: 1634957 (Python Code)

Max Activating Token Index: 906

Text #7

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0666. Min Act: -0.0000

Data Index: 1644919 (Python Code)

Max Activating Token Index: 854

Text #8

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0563. Min Act: -0.0000

Data Index: 326843 (C4 (Web Text))

Max Activating Token Index: 626

Text #9

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0571. Min Act: -0.0000

Data Index: 1305762 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0587. Min Act: -0.0000

Data Index: 1116318 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1566083 (Python Code)

Max Activating Token Index: 69

Text #12

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0571. Min Act: -0.0000

Data Index: 1057504 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0603. Min Act: -0.0001

Data Index: 1528049 (Python Code)

Max Activating Token Index: 961

Text #14

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0554. Min Act: -0.0000

Data Index: 1520753 (Python Code)

Max Activating Token Index: 444

Text #15

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0534. Min Act: -0.0001

Data Index: 1421896 (Python Code)

Max Activating Token Index: 516

Text #16

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0547. Min Act: -0.0000

Data Index: 1621562 (Python Code)

Max Activating Token Index: 682

Text #17

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0519. Min Act: -0.0001

Data Index: 1524554 (Python Code)

Max Activating Token Index: 530

Text #18

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0568. Min Act: -0.0000

Data Index: 516962 (C4 (Web Text))

Max Activating Token Index: 770

Text #19

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0567. Min Act: -0.0000

Data Index: 1516786 (Python Code)

Max Activating Token Index: 145