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

Dataset: The Pile

Neuron 3202 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: 0.2063. Min Range: -0.2063

Max Act: 0.1903. Min Act: -0.0000

Data Index: 255158 (The Pile)

Max Activating Token Index: 121

Text #1

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.2063. Min Act: -0.0000

Data Index: 164304 (The Pile)

Max Activating Token Index: 1007

Text #2

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1939. Min Act: -0.0000

Data Index: 218433 (The Pile)

Max Activating Token Index: 893

Text #3

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1925. Min Act: -0.0000

Data Index: 211593 (The Pile)

Max Activating Token Index: 807

Text #4

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1700. Min Act: -0.0000

Data Index: 1952229 (The Pile)

Max Activating Token Index: 885

Text #5

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.2021. Min Act: -0.0000

Data Index: 1059792 (The Pile)

Max Activating Token Index: 25

Text #6

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1753. Min Act: -0.0000

Data Index: 79953 (The Pile)

Max Activating Token Index: 708

Text #7

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1371743 (The Pile)

Max Activating Token Index: 631

Text #8

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1740. Min Act: -0.0000

Data Index: 34768 (The Pile)

Max Activating Token Index: 923

Text #9

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1825. Min Act: -0.0000

Data Index: 875863 (The Pile)

Max Activating Token Index: 1011

Text #10

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1637. Min Act: -0.0000

Data Index: 754980 (The Pile)

Max Activating Token Index: 402

Text #11

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1504. Min Act: -0.0000

Data Index: 719043 (The Pile)

Max Activating Token Index: 582

Text #12

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1720. Min Act: -0.0000

Data Index: 1936311 (The Pile)

Max Activating Token Index: 590

Text #13

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1637. Min Act: -0.0000

Data Index: 1479677 (The Pile)

Max Activating Token Index: 284

Text #14

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1630. Min Act: -0.0000

Data Index: 66713 (The Pile)

Max Activating Token Index: 198

Text #15

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1616. Min Act: -0.0000

Data Index: 439668 (The Pile)

Max Activating Token Index: 90

Text #16

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1629. Min Act: -0.0000

Data Index: 25713 (The Pile)

Max Activating Token Index: 167

Text #17

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1552. Min Act: -0.0000

Data Index: 99628 (The Pile)

Max Activating Token Index: 278

Text #18

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1546. Min Act: -0.0000

Data Index: 922983 (The Pile)

Max Activating Token Index: 390

Text #19

Max Range: 0.2063. Min Range: -0.2063

Max Act: 0.1542. Min Act: -0.0000

Data Index: 249451 (The Pile)

Max Activating Token Index: 686