Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 887 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2639. Min Act: -0.0001

Data Index: 1594918 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.2147. Min Act: -0.0001

Data Index: 1530477 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1911. Min Act: -0.0001

Data Index: 1482920 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1772. Min Act: -0.0001

Data Index: 1364642 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1833. Min Act: -0.0001

Data Index: 1516738 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1825. Min Act: -0.0001

Data Index: 1505329 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1826. Min Act: -0.0001

Data Index: 1400372 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1783. Min Act: -0.0001

Data Index: 1441051 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1765. Min Act: -0.0001

Data Index: 797649 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1759. Min Act: -0.0001

Data Index: 647958 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1741. Min Act: -0.0001

Data Index: 1360452 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1736. Min Act: -0.0001

Data Index: 1551879 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1661. Min Act: -0.0001

Data Index: 1005231 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1715. Min Act: -0.0001

Data Index: 733280 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1772. Min Act: -0.0001

Data Index: 880644 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1695. Min Act: -0.0001

Data Index: 313513 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1625. Min Act: -0.0001

Data Index: 649981 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1667. Min Act: -0.0001

Data Index: 452340 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1639. Min Act: -0.0001

Data Index: 1431395 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.2639. Min Range: -0.2639

Max Act: 0.1636. Min Act: -0.0001

Data Index: 1381747 (Python Code)

Max Activating Token Index: 1023