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

Dataset: The Pile

Neuron 1253 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.6738. Min Act: -0.0000

Data Index: 1731729 (The Pile)

Max Activating Token Index: 147

Text #1

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.2416. Min Act: -0.0000

Data Index: 1058742 (The Pile)

Max Activating Token Index: 489

Text #2

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.5315. Min Act: -0.0000

Data Index: 1686734 (The Pile)

Max Activating Token Index: 178

Text #3

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.1373. Min Act: -0.0000

Data Index: 1599138 (The Pile)

Max Activating Token Index: 515

Text #4

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.0286. Min Act: -0.0000

Data Index: 585041 (The Pile)

Max Activating Token Index: 749

Text #5

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.1373. Min Act: -0.0000

Data Index: 1660634 (The Pile)

Max Activating Token Index: 420

Text #6

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.4024. Min Act: -0.0000

Data Index: 1019827 (The Pile)

Max Activating Token Index: 264

Text #7

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.1634. Min Act: -0.0000

Data Index: 1921603 (The Pile)

Max Activating Token Index: 681

Text #8

Max Range: 3.6738. Min Range: -3.6738

Max Act: 2.8448. Min Act: -0.0000

Data Index: 1147100 (The Pile)

Max Activating Token Index: 471

Text #9

Max Range: 3.6738. Min Range: -3.6738

Max Act: 2.3492. Min Act: -0.0000

Data Index: 997027 (The Pile)

Max Activating Token Index: 960

Text #10

Max Range: 3.6738. Min Range: -3.6738

Max Act: 2.5337. Min Act: -0.0000

Data Index: 1786366 (The Pile)

Max Activating Token Index: 131

Text #11

Max Range: 3.6738. Min Range: -3.6738

Max Act: 2.6595. Min Act: -0.0000

Data Index: 1189511 (The Pile)

Max Activating Token Index: 89

Text #12

Max Range: 3.6738. Min Range: -3.6738

Max Act: 2.6590. Min Act: -0.0000

Data Index: 1920273 (The Pile)

Max Activating Token Index: 81

Text #13

Max Range: 3.6738. Min Range: -3.6738

Max Act: 2.5168. Min Act: -0.0000

Data Index: 326802 (The Pile)

Max Activating Token Index: 1011

Text #14

Max Range: 3.6738. Min Range: -3.6738

Max Act: 2.0588. Min Act: -0.0000

Data Index: 1540764 (The Pile)

Max Activating Token Index: 945

Text #15

Max Range: 3.6738. Min Range: -3.6738

Max Act: 2.4200. Min Act: -0.0000

Data Index: 391212 (The Pile)

Max Activating Token Index: 950

Text #16

Max Range: 3.6738. Min Range: -3.6738

Max Act: 2.3854. Min Act: -0.0000

Data Index: 320579 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 3.6738. Min Range: -3.6738

Max Act: 2.2348. Min Act: -0.0000

Data Index: 1280386 (The Pile)

Max Activating Token Index: 210

Text #18

Max Range: 3.6738. Min Range: -3.6738

Max Act: 2.4597. Min Act: -0.0000

Data Index: 1993539 (The Pile)

Max Activating Token Index: 562

Text #19

Max Range: 3.6738. Min Range: -3.6738

Max Act: 2.1726. Min Act: -0.0000

Data Index: 1694671 (The Pile)

Max Activating Token Index: 531