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

Dataset: The Pile

Neuron 2526 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0797. Min Act: -0.0000

Data Index: 1403352 (The Pile)

Max Activating Token Index: 2

Text #1

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0689. Min Act: -0.0000

Data Index: 331161 (The Pile)

Max Activating Token Index: 12

Text #2

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0662. Min Act: -0.0000

Data Index: 285145 (The Pile)

Max Activating Token Index: 24

Text #3

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0651. Min Act: -0.0000

Data Index: 922330 (The Pile)

Max Activating Token Index: 50

Text #4

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0646. Min Act: -0.0000

Data Index: 855927 (The Pile)

Max Activating Token Index: 5

Text #5

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0645. Min Act: -0.0000

Data Index: 1294408 (The Pile)

Max Activating Token Index: 21

Text #6

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0644. Min Act: -0.0000

Data Index: 1618237 (The Pile)

Max Activating Token Index: 46

Text #7

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0638. Min Act: -0.0000

Data Index: 1937723 (The Pile)

Max Activating Token Index: 715

Text #8

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0634. Min Act: -0.0000

Data Index: 34672 (The Pile)

Max Activating Token Index: 3

Text #9

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0641. Min Act: -0.0000

Data Index: 1640692 (The Pile)

Max Activating Token Index: 69

Text #10

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0614. Min Act: -0.0000

Data Index: 853123 (The Pile)

Max Activating Token Index: 3

Text #11

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1384896 (The Pile)

Max Activating Token Index: 4

Text #12

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1929871 (The Pile)

Max Activating Token Index: 16

Text #13

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0612. Min Act: -0.0000

Data Index: 895613 (The Pile)

Max Activating Token Index: 24

Text #14

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0589. Min Act: -0.0000

Data Index: 936166 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0607. Min Act: -0.0000

Data Index: 1403208 (The Pile)

Max Activating Token Index: 455

Text #16

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0626. Min Act: -0.0000

Data Index: 56871 (The Pile)

Max Activating Token Index: 13

Text #17

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0601. Min Act: -0.0000

Data Index: 1900410 (The Pile)

Max Activating Token Index: 466

Text #18

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0600. Min Act: -0.0000

Data Index: 956754 (The Pile)

Max Activating Token Index: 4

Text #19

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0600. Min Act: -0.0000

Data Index: 690103 (The Pile)

Max Activating Token Index: 20