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

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

Neuron 1683 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: 0.2240. Min Range: -0.2240

Max Act: 0.2209. Min Act: -0.0001

Data Index: 82806 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.2220. Min Act: -0.0001

Data Index: 44556 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.2240. Min Act: -0.0001

Data Index: 522858 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.2163. Min Act: -0.0001

Data Index: 221685 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1784. Min Act: -0.0001

Data Index: 245536 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1772. Min Act: -0.0001

Data Index: 768706 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1802. Min Act: -0.0001

Data Index: 673189 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1759. Min Act: -0.0001

Data Index: 953366 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1734. Min Act: -0.0001

Data Index: 519519 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1684. Min Act: -0.0001

Data Index: 715941 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1700. Min Act: -0.0001

Data Index: 1185352 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1557. Min Act: -0.0001

Data Index: 1029459 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1623. Min Act: -0.0001

Data Index: 1131589 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1708. Min Act: -0.0001

Data Index: 269245 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1538. Min Act: -0.0001

Data Index: 1508390 (Python Code)

Max Activating Token Index: 818

Text #15

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1539. Min Act: -0.0001

Data Index: 1587688 (Python Code)

Max Activating Token Index: 854

Text #16

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1551. Min Act: -0.0001

Data Index: 518304 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1609. Min Act: -0.0001

Data Index: 21479 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1667. Min Act: -0.0001

Data Index: 13133 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1654. Min Act: -0.0001

Data Index: 1590813 (Python Code)

Max Activating Token Index: 949