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

Dataset: The Pile

Neuron 675 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: 1.0033. Min Range: -1.0033

Max Act: 1.0033. Min Act: 0.0000

Data Index: 1168649 (The Pile)

Max Activating Token Index: 577

Text #1

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.9274. Min Act: 0.0000

Data Index: 307771 (The Pile)

Max Activating Token Index: 861

Text #2

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.8824. Min Act: 0.0000

Data Index: 1986635 (The Pile)

Max Activating Token Index: 703

Text #3

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7727. Min Act: -0.0000

Data Index: 559584 (The Pile)

Max Activating Token Index: 364

Text #4

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7571. Min Act: -0.0000

Data Index: 1211001 (The Pile)

Max Activating Token Index: 899

Text #5

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7808. Min Act: -0.0000

Data Index: 484924 (The Pile)

Max Activating Token Index: 664

Text #6

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.8006. Min Act: 0.0000

Data Index: 1372612 (The Pile)

Max Activating Token Index: 137

Text #7

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7518. Min Act: 0.0000

Data Index: 1999440 (The Pile)

Max Activating Token Index: 91

Text #8

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7231. Min Act: 0.0000

Data Index: 1835172 (The Pile)

Max Activating Token Index: 341

Text #9

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.6871. Min Act: 0.0000

Data Index: 555111 (The Pile)

Max Activating Token Index: 829

Text #10

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7053. Min Act: 0.0000

Data Index: 360529 (The Pile)

Max Activating Token Index: 555

Text #11

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7172. Min Act: 0.0000

Data Index: 654998 (The Pile)

Max Activating Token Index: 69

Text #12

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.6849. Min Act: 0.0000

Data Index: 968111 (The Pile)

Max Activating Token Index: 324

Text #13

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1680119 (The Pile)

Max Activating Token Index: 730

Text #14

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.6797. Min Act: -0.0000

Data Index: 61040 (The Pile)

Max Activating Token Index: 661

Text #15

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.6709. Min Act: -0.0000

Data Index: 737929 (The Pile)

Max Activating Token Index: 562

Text #16

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1469455 (The Pile)

Max Activating Token Index: 161

Text #17

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.6584. Min Act: 0.0000

Data Index: 553576 (The Pile)

Max Activating Token Index: 635

Text #18

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.6834. Min Act: -0.0000

Data Index: 654123 (The Pile)

Max Activating Token Index: 276

Text #19

Max Range: 1.0033. Min Range: -1.0033

Max Act: 0.6635. Min Act: 0.0000

Data Index: 132404 (The Pile)

Max Activating Token Index: 663