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

Dataset: The Pile

Neuron 1852 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: 0.7426. Min Range: -0.7426

Max Act: 0.7129. Min Act: -0.0000

Data Index: 874691 (The Pile)

Max Activating Token Index: 511

Text #1

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.7083. Min Act: -0.0000

Data Index: 266545 (The Pile)

Max Activating Token Index: 961

Text #2

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.7001. Min Act: -0.0000

Data Index: 1497104 (The Pile)

Max Activating Token Index: 833

Text #3

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6639. Min Act: -0.0000

Data Index: 740075 (The Pile)

Max Activating Token Index: 457

Text #4

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6330. Min Act: -0.0000

Data Index: 1489896 (The Pile)

Max Activating Token Index: 794

Text #5

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.7426. Min Act: -0.0000

Data Index: 1831570 (The Pile)

Max Activating Token Index: 759

Text #6

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6111. Min Act: -0.0000

Data Index: 1729 (The Pile)

Max Activating Token Index: 315

Text #7

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1336166 (The Pile)

Max Activating Token Index: 792

Text #8

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6277. Min Act: -0.0000

Data Index: 430172 (The Pile)

Max Activating Token Index: 251

Text #9

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6041. Min Act: -0.0000

Data Index: 1992659 (The Pile)

Max Activating Token Index: 851

Text #10

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6841. Min Act: -0.0000

Data Index: 937163 (The Pile)

Max Activating Token Index: 901

Text #11

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6412. Min Act: -0.0000

Data Index: 737496 (The Pile)

Max Activating Token Index: 837

Text #12

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5922. Min Act: -0.0000

Data Index: 197739 (The Pile)

Max Activating Token Index: 775

Text #13

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1463678 (The Pile)

Max Activating Token Index: 176

Text #14

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6299. Min Act: -0.0000

Data Index: 560697 (The Pile)

Max Activating Token Index: 255

Text #15

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6223. Min Act: -0.0000

Data Index: 324191 (The Pile)

Max Activating Token Index: 858

Text #16

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6003. Min Act: -0.0000

Data Index: 243707 (The Pile)

Max Activating Token Index: 817

Text #17

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6149. Min Act: -0.0000

Data Index: 1331788 (The Pile)

Max Activating Token Index: 525

Text #18

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.6163. Min Act: -0.0000

Data Index: 427719 (The Pile)

Max Activating Token Index: 674

Text #19

Max Range: 0.7426. Min Range: -0.7426

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1905586 (The Pile)

Max Activating Token Index: 166