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

Dataset: The Pile

Neuron 3417 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.7003. Min Act: -0.0000

Data Index: 1496456 (The Pile)

Max Activating Token Index: 769

Text #1

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6947. Min Act: -0.0000

Data Index: 1035988 (The Pile)

Max Activating Token Index: 527

Text #2

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6564. Min Act: -0.0000

Data Index: 527628 (The Pile)

Max Activating Token Index: 931

Text #3

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6741. Min Act: -0.0000

Data Index: 203563 (The Pile)

Max Activating Token Index: 410

Text #4

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6721. Min Act: -0.0000

Data Index: 1502598 (The Pile)

Max Activating Token Index: 18

Text #5

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5808. Min Act: -0.0000

Data Index: 995379 (The Pile)

Max Activating Token Index: 803

Text #6

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1982987 (The Pile)

Max Activating Token Index: 135

Text #7

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5978. Min Act: -0.0000

Data Index: 1222186 (The Pile)

Max Activating Token Index: 659

Text #8

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5605. Min Act: -0.0000

Data Index: 1285238 (The Pile)

Max Activating Token Index: 859

Text #9

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5371. Min Act: -0.0000

Data Index: 778200 (The Pile)

Max Activating Token Index: 878

Text #10

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5672. Min Act: -0.0000

Data Index: 588492 (The Pile)

Max Activating Token Index: 325

Text #11

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5993. Min Act: -0.0000

Data Index: 947122 (The Pile)

Max Activating Token Index: 58

Text #12

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1610010 (The Pile)

Max Activating Token Index: 590

Text #13

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5209. Min Act: -0.0000

Data Index: 862410 (The Pile)

Max Activating Token Index: 33

Text #14

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5493. Min Act: -0.0000

Data Index: 1983659 (The Pile)

Max Activating Token Index: 721

Text #15

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.6035. Min Act: -0.0000

Data Index: 148658 (The Pile)

Max Activating Token Index: 231

Text #16

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5051. Min Act: -0.0000

Data Index: 456805 (The Pile)

Max Activating Token Index: 50

Text #17

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5804. Min Act: -0.0000

Data Index: 1647751 (The Pile)

Max Activating Token Index: 58

Text #18

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5329. Min Act: -0.0000

Data Index: 752509 (The Pile)

Max Activating Token Index: 897

Text #19

Max Range: 0.7003. Min Range: -0.7003

Max Act: 0.5744. Min Act: -0.0000

Data Index: 1714703 (The Pile)

Max Activating Token Index: 212