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

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

Neuron 805 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.2104. Min Act: -0.0001

Data Index: 1059359 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1983. Min Act: -0.0000

Data Index: 221302 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1946. Min Act: -0.0001

Data Index: 884836 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1935. Min Act: -0.0000

Data Index: 935778 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1999. Min Act: -0.0001

Data Index: 574846 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1961. Min Act: -0.0000

Data Index: 228721 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1950. Min Act: -0.0001

Data Index: 568758 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1877. Min Act: -0.0000

Data Index: 452189 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1990. Min Act: -0.0001

Data Index: 1152701 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1847. Min Act: 0.0000

Data Index: 1126530 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1847. Min Act: -0.0001

Data Index: 636135 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1841. Min Act: -0.0000

Data Index: 774834 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1700. Min Act: -0.0000

Data Index: 1216225 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1855. Min Act: -0.0001

Data Index: 101831 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1810. Min Act: -0.0000

Data Index: 385155 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1299517 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1798. Min Act: -0.0001

Data Index: 94385 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1762. Min Act: -0.0000

Data Index: 1644273 (Python Code)

Max Activating Token Index: 75

Text #18

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1708. Min Act: -0.0001

Data Index: 1087619 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 0.2104. Min Range: -0.2104

Max Act: 0.1742. Min Act: -0.0001

Data Index: 514540 (C4 (Web Text))

Max Activating Token Index: 734