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

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

Neuron 27 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1962. Min Act: -0.0001

Data Index: 1428020 (Python Code)

Max Activating Token Index: 766

Text #1

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1975. Min Act: -0.0001

Data Index: 1455381 (Python Code)

Max Activating Token Index: 82

Text #2

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1794. Min Act: -0.0001

Data Index: 1396060 (Python Code)

Max Activating Token Index: 530

Text #3

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1649. Min Act: -0.0001

Data Index: 1570326 (Python Code)

Max Activating Token Index: 740

Text #4

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1950. Min Act: -0.0001

Data Index: 1372666 (Python Code)

Max Activating Token Index: 703

Text #5

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1884. Min Act: -0.0001

Data Index: 1622041 (Python Code)

Max Activating Token Index: 964

Text #6

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1874. Min Act: -0.0001

Data Index: 1639432 (Python Code)

Max Activating Token Index: 487

Text #7

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1804. Min Act: -0.0001

Data Index: 1611368 (Python Code)

Max Activating Token Index: 959

Text #8

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1915. Min Act: -0.0001

Data Index: 1440474 (Python Code)

Max Activating Token Index: 698

Text #9

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1830. Min Act: -0.0001

Data Index: 1610988 (Python Code)

Max Activating Token Index: 722

Text #10

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1889. Min Act: -0.0001

Data Index: 1491319 (Python Code)

Max Activating Token Index: 742

Text #11

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1826. Min Act: -0.0001

Data Index: 1404832 (Python Code)

Max Activating Token Index: 613

Text #12

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1827. Min Act: -0.0001

Data Index: 1366113 (Python Code)

Max Activating Token Index: 651

Text #13

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1853. Min Act: -0.0001

Data Index: 1613109 (Python Code)

Max Activating Token Index: 603

Text #14

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1722. Min Act: -0.0001

Data Index: 1647017 (Python Code)

Max Activating Token Index: 858

Text #15

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1747. Min Act: -0.0001

Data Index: 1369915 (Python Code)

Max Activating Token Index: 524

Text #16

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1732. Min Act: -0.0001

Data Index: 1571240 (Python Code)

Max Activating Token Index: 272

Text #17

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1791. Min Act: -0.0001

Data Index: 1538577 (Python Code)

Max Activating Token Index: 410

Text #18

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1744. Min Act: -0.0001

Data Index: 1591519 (Python Code)

Max Activating Token Index: 552

Text #19

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1794. Min Act: -0.0001

Data Index: 1556223 (Python Code)

Max Activating Token Index: 717