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

Dataset: The Pile

Neuron 713 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2660. Min Act: 0.0000

Data Index: 98756 (The Pile)

Max Activating Token Index: 38

Text #1

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1411681 (The Pile)

Max Activating Token Index: 238

Text #2

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2032. Min Act: -0.0000

Data Index: 1908308 (The Pile)

Max Activating Token Index: 440

Text #3

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2053. Min Act: 0.0000

Data Index: 360091 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2000. Min Act: -0.0000

Data Index: 1330013 (The Pile)

Max Activating Token Index: 940

Text #5

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1043682 (The Pile)

Max Activating Token Index: 369

Text #6

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1885. Min Act: -0.0000

Data Index: 123459 (The Pile)

Max Activating Token Index: 508

Text #7

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1749. Min Act: -0.0000

Data Index: 212182 (The Pile)

Max Activating Token Index: 427

Text #8

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1559. Min Act: -0.0000

Data Index: 118428 (The Pile)

Max Activating Token Index: 414

Text #9

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1583. Min Act: -0.0000

Data Index: 76452 (The Pile)

Max Activating Token Index: 693

Text #10

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1695. Min Act: 0.0000

Data Index: 488765 (The Pile)

Max Activating Token Index: 116

Text #11

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1677. Min Act: -0.0000

Data Index: 1518510 (The Pile)

Max Activating Token Index: 710

Text #12

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1721. Min Act: -0.0000

Data Index: 1355494 (The Pile)

Max Activating Token Index: 689

Text #13

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1609. Min Act: -0.0000

Data Index: 1110057 (The Pile)

Max Activating Token Index: 408

Text #14

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1664. Min Act: -0.0000

Data Index: 1333523 (The Pile)

Max Activating Token Index: 1009

Text #15

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1584. Min Act: 0.0000

Data Index: 865426 (The Pile)

Max Activating Token Index: 933

Text #16

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1548. Min Act: -0.0000

Data Index: 1874248 (The Pile)

Max Activating Token Index: 173

Text #17

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1546. Min Act: -0.0000

Data Index: 354201 (The Pile)

Max Activating Token Index: 315

Text #18

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1551. Min Act: -0.0000

Data Index: 1705889 (The Pile)

Max Activating Token Index: 598

Text #19

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1534. Min Act: -0.0000

Data Index: 249981 (The Pile)

Max Activating Token Index: 336