Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1807 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2797. Min Act: -0.0001

Data Index: 59964 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2632. Min Act: -0.0001

Data Index: 1246828 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2627. Min Act: -0.0001

Data Index: 475029 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2370. Min Act: -0.0000

Data Index: 402572 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2061. Min Act: -0.0001

Data Index: 813797 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1902. Min Act: -0.0001

Data Index: 404106 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2112. Min Act: -0.0001

Data Index: 689401 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.2020. Min Act: -0.0001

Data Index: 1176013 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1938. Min Act: -0.0000

Data Index: 205001 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1680. Min Act: -0.0001

Data Index: 1292713 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1840. Min Act: -0.0000

Data Index: 82361 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1922. Min Act: -0.0001

Data Index: 1282986 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1829. Min Act: -0.0001

Data Index: 312074 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1786. Min Act: -0.0001

Data Index: 278973 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1835. Min Act: -0.0001

Data Index: 463213 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1747. Min Act: -0.0000

Data Index: 999073 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1780. Min Act: -0.0001

Data Index: 986793 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1774. Min Act: -0.0001

Data Index: 91384 (C4 (Web Text))

Max Activating Token Index: 451

Text #18

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1843. Min Act: -0.0001

Data Index: 1019954 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 0.2797. Min Range: -0.2797

Max Act: 0.1742. Min Act: -0.0001

Data Index: 828169 (C4 (Web Text))

Max Activating Token Index: 885