Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2531 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.3660. Min Act: -0.0000

Data Index: 1151446 (The Pile)

Max Activating Token Index: 86

Text #1

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2289. Min Act: -0.0000

Data Index: 667957 (The Pile)

Max Activating Token Index: 594

Text #2

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2083. Min Act: -0.0000

Data Index: 905237 (The Pile)

Max Activating Token Index: 742

Text #3

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2074. Min Act: -0.0000

Data Index: 379585 (The Pile)

Max Activating Token Index: 59

Text #4

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.1831. Min Act: -0.0000

Data Index: 1766701 (The Pile)

Max Activating Token Index: 317

Text #5

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.1556. Min Act: -0.0000

Data Index: 1125544 (The Pile)

Max Activating Token Index: 866

Text #6

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2008. Min Act: -0.0000

Data Index: 1967298 (The Pile)

Max Activating Token Index: 27

Text #7

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.1873. Min Act: -0.0000

Data Index: 36605 (The Pile)

Max Activating Token Index: 207

Text #8

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.1849. Min Act: -0.0000

Data Index: 1542237 (The Pile)

Max Activating Token Index: 585

Text #9

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.1830. Min Act: -0.0000

Data Index: 334852 (The Pile)

Max Activating Token Index: 296

Text #10

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.1866. Min Act: -0.0000

Data Index: 1734042 (The Pile)

Max Activating Token Index: 179

Text #11

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.1867. Min Act: -0.0000

Data Index: 504223 (The Pile)

Max Activating Token Index: 215

Text #12

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.1786. Min Act: -0.0000

Data Index: 1945932 (The Pile)

Max Activating Token Index: 447

Text #13

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.1763. Min Act: -0.0000

Data Index: 1420955 (The Pile)

Max Activating Token Index: 306

Text #14

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.1790. Min Act: -0.0000

Data Index: 1165717 (The Pile)

Max Activating Token Index: 965

Text #15

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.1794. Min Act: -0.0000

Data Index: 1466724 (The Pile)

Max Activating Token Index: 549

Text #16

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.2066. Min Act: -0.0000

Data Index: 1365176 (The Pile)

Max Activating Token Index: 141

Text #17

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.1838. Min Act: -0.0000

Data Index: 578808 (The Pile)

Max Activating Token Index: 911

Text #18

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.1704. Min Act: -0.0000

Data Index: 1026719 (The Pile)

Max Activating Token Index: 396

Text #19

Max Range: 0.3660. Min Range: -0.3660

Max Act: 0.1629. Min Act: -0.0000

Data Index: 1655404 (The Pile)

Max Activating Token Index: 419