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

Dataset: The Pile

Neuron 2559 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1997. Min Act: -0.0000

Data Index: 1884771 (The Pile)

Max Activating Token Index: 598

Text #1

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1966041 (The Pile)

Max Activating Token Index: 343

Text #2

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1961. Min Act: -0.0000

Data Index: 76882 (The Pile)

Max Activating Token Index: 787

Text #3

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1924. Min Act: -0.0000

Data Index: 909855 (The Pile)

Max Activating Token Index: 546

Text #4

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1891. Min Act: -0.0000

Data Index: 998976 (The Pile)

Max Activating Token Index: 631

Text #5

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1919. Min Act: -0.0000

Data Index: 1757689 (The Pile)

Max Activating Token Index: 346

Text #6

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1927. Min Act: -0.0000

Data Index: 1795367 (The Pile)

Max Activating Token Index: 350

Text #7

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1852. Min Act: -0.0000

Data Index: 282962 (The Pile)

Max Activating Token Index: 97

Text #8

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1828. Min Act: -0.0000

Data Index: 328982 (The Pile)

Max Activating Token Index: 159

Text #9

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1811. Min Act: -0.0000

Data Index: 1369473 (The Pile)

Max Activating Token Index: 598

Text #10

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1835. Min Act: -0.0000

Data Index: 333701 (The Pile)

Max Activating Token Index: 284

Text #11

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1700. Min Act: -0.0000

Data Index: 1168864 (The Pile)

Max Activating Token Index: 617

Text #12

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1281983 (The Pile)

Max Activating Token Index: 706

Text #13

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1767. Min Act: -0.0000

Data Index: 425836 (The Pile)

Max Activating Token Index: 223

Text #14

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1620. Min Act: -0.0000

Data Index: 131149 (The Pile)

Max Activating Token Index: 854

Text #15

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1631. Min Act: -0.0000

Data Index: 143685 (The Pile)

Max Activating Token Index: 299

Text #16

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1685. Min Act: -0.0000

Data Index: 1201399 (The Pile)

Max Activating Token Index: 594

Text #17

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1550. Min Act: -0.0000

Data Index: 80118 (The Pile)

Max Activating Token Index: 374

Text #18

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1516. Min Act: -0.0000

Data Index: 1132789 (The Pile)

Max Activating Token Index: 515

Text #19

Max Range: 0.2087. Min Range: -0.2087

Max Act: 0.1510. Min Act: -0.0000

Data Index: 26168 (The Pile)

Max Activating Token Index: 221