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

Dataset: The Pile

Neuron 553 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: 0.6537. Min Range: -0.6537

Max Act: 0.6537. Min Act: -0.0000

Data Index: 330003 (The Pile)

Max Activating Token Index: 67

Text #1

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.6481. Min Act: -0.0000

Data Index: 1168927 (The Pile)

Max Activating Token Index: 423

Text #2

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5936. Min Act: -0.0000

Data Index: 264542 (The Pile)

Max Activating Token Index: 280

Text #3

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.6243. Min Act: 0.0000

Data Index: 1924706 (The Pile)

Max Activating Token Index: 151

Text #4

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.6021. Min Act: -0.0000

Data Index: 1411988 (The Pile)

Max Activating Token Index: 507

Text #5

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5752. Min Act: -0.0000

Data Index: 1172808 (The Pile)

Max Activating Token Index: 262

Text #6

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5566. Min Act: -0.0000

Data Index: 895983 (The Pile)

Max Activating Token Index: 743

Text #7

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5370. Min Act: -0.0000

Data Index: 691986 (The Pile)

Max Activating Token Index: 101

Text #8

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5650. Min Act: -0.0000

Data Index: 905246 (The Pile)

Max Activating Token Index: 482

Text #9

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.6229. Min Act: -0.0000

Data Index: 1023504 (The Pile)

Max Activating Token Index: 32

Text #10

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5199. Min Act: -0.0000

Data Index: 151238 (The Pile)

Max Activating Token Index: 730

Text #11

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5681. Min Act: -0.0000

Data Index: 865692 (The Pile)

Max Activating Token Index: 910

Text #12

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5520. Min Act: -0.0000

Data Index: 842831 (The Pile)

Max Activating Token Index: 545

Text #13

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5278. Min Act: -0.0000

Data Index: 1603218 (The Pile)

Max Activating Token Index: 901

Text #14

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5651. Min Act: -0.0000

Data Index: 1610840 (The Pile)

Max Activating Token Index: 764

Text #15

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5162. Min Act: -0.0000

Data Index: 760015 (The Pile)

Max Activating Token Index: 626

Text #16

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.4950. Min Act: -0.0000

Data Index: 1959817 (The Pile)

Max Activating Token Index: 574

Text #17

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.4883. Min Act: -0.0000

Data Index: 1892887 (The Pile)

Max Activating Token Index: 818

Text #18

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1981097 (The Pile)

Max Activating Token Index: 467

Text #19

Max Range: 0.6537. Min Range: -0.6537

Max Act: 0.5019. Min Act: -0.0000

Data Index: 687889 (The Pile)

Max Activating Token Index: 568