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

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

Neuron 2974 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1967. Min Act: -0.0001

Data Index: 148670 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1874. Min Act: -0.0001

Data Index: 1228728 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1795. Min Act: -0.0001

Data Index: 984462 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1736. Min Act: -0.0001

Data Index: 793888 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1809. Min Act: -0.0000

Data Index: 718234 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1733. Min Act: 0.0002

Data Index: 249791 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1690. Min Act: -0.0001

Data Index: 1120280 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1628. Min Act: -0.0001

Data Index: 213911 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1656. Min Act: -0.0001

Data Index: 811052 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1667. Min Act: -0.0000

Data Index: 110309 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1568. Min Act: -0.0000

Data Index: 287139 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1578. Min Act: -0.0001

Data Index: 206900 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1645. Min Act: -0.0001

Data Index: 597421 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1736. Min Act: -0.0001

Data Index: 564465 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1639. Min Act: 0.0000

Data Index: 93988 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1651. Min Act: -0.0001

Data Index: 1054981 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1587. Min Act: -0.0000

Data Index: 591848 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1585. Min Act: -0.0001

Data Index: 719717 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1544. Min Act: -0.0001

Data Index: 610367 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.1967. Min Range: -0.1967

Max Act: 0.1530. Min Act: -0.0001

Data Index: 1155870 (C4 (Web Text))

Max Activating Token Index: 800