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

Dataset: The Pile

Neuron 3117 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2940. Min Act: -0.0000

Data Index: 1137698 (The Pile)

Max Activating Token Index: 860

Text #1

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2477. Min Act: -0.0000

Data Index: 127997 (The Pile)

Max Activating Token Index: 763

Text #2

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2653. Min Act: -0.0000

Data Index: 593464 (The Pile)

Max Activating Token Index: 1005

Text #3

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2611. Min Act: -0.0000

Data Index: 781297 (The Pile)

Max Activating Token Index: 1003

Text #4

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2899. Min Act: -0.0000

Data Index: 314125 (The Pile)

Max Activating Token Index: 804

Text #5

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2207. Min Act: -0.0000

Data Index: 1747641 (The Pile)

Max Activating Token Index: 779

Text #6

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2416. Min Act: -0.0000

Data Index: 673987 (The Pile)

Max Activating Token Index: 940

Text #7

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2305. Min Act: -0.0000

Data Index: 190044 (The Pile)

Max Activating Token Index: 487

Text #8

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1818355 (The Pile)

Max Activating Token Index: 866

Text #9

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2403. Min Act: -0.0000

Data Index: 818225 (The Pile)

Max Activating Token Index: 425

Text #10

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2328. Min Act: -0.0000

Data Index: 481146 (The Pile)

Max Activating Token Index: 239

Text #11

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2001. Min Act: -0.0000

Data Index: 1108001 (The Pile)

Max Activating Token Index: 849

Text #12

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2090. Min Act: -0.0000

Data Index: 1833466 (The Pile)

Max Activating Token Index: 898

Text #13

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1910. Min Act: -0.0000

Data Index: 456955 (The Pile)

Max Activating Token Index: 600

Text #14

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1740. Min Act: -0.0000

Data Index: 1451426 (The Pile)

Max Activating Token Index: 739

Text #15

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1989. Min Act: -0.0000

Data Index: 1533047 (The Pile)

Max Activating Token Index: 404

Text #16

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2147. Min Act: -0.0000

Data Index: 1248056 (The Pile)

Max Activating Token Index: 1018

Text #17

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1817. Min Act: -0.0000

Data Index: 473115 (The Pile)

Max Activating Token Index: 139

Text #18

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1244056 (The Pile)

Max Activating Token Index: 925

Text #19

Max Range: 0.2940. Min Range: -0.2940

Max Act: 0.1935. Min Act: -0.0000

Data Index: 1741156 (The Pile)

Max Activating Token Index: 897