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

Dataset: The Pile

Neuron 2496 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.3390. Min Act: -0.0000

Data Index: 27453 (The Pile)

Max Activating Token Index: 687

Text #1

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.0728. Min Act: -0.0000

Data Index: 1455344 (The Pile)

Max Activating Token Index: 708

Text #2

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.2804. Min Act: -0.0000

Data Index: 1023108 (The Pile)

Max Activating Token Index: 885

Text #3

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1036. Min Act: -0.0000

Data Index: 545154 (The Pile)

Max Activating Token Index: 166

Text #4

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.1844. Min Act: -0.0000

Data Index: 1227459 (The Pile)

Max Activating Token Index: 249

Text #5

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.9440. Min Act: -0.0000

Data Index: 730303 (The Pile)

Max Activating Token Index: 878

Text #6

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.0270. Min Act: -0.0000

Data Index: 1904477 (The Pile)

Max Activating Token Index: 105

Text #7

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.9474. Min Act: -0.0000

Data Index: 1211282 (The Pile)

Max Activating Token Index: 576

Text #8

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.0037. Min Act: -0.0000

Data Index: 1478093 (The Pile)

Max Activating Token Index: 644

Text #9

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.8769. Min Act: -0.0000

Data Index: 1283565 (The Pile)

Max Activating Token Index: 15

Text #10

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.8871. Min Act: -0.0000

Data Index: 992761 (The Pile)

Max Activating Token Index: 984

Text #11

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.9616. Min Act: -0.0000

Data Index: 1642353 (The Pile)

Max Activating Token Index: 71

Text #12

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.9690. Min Act: -0.0000

Data Index: 1655347 (The Pile)

Max Activating Token Index: 272

Text #13

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.9463. Min Act: -0.0000

Data Index: 752659 (The Pile)

Max Activating Token Index: 625

Text #14

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.9218. Min Act: -0.0000

Data Index: 1769933 (The Pile)

Max Activating Token Index: 890

Text #15

Max Range: 1.3390. Min Range: -1.3390

Max Act: 1.0083. Min Act: -0.0000

Data Index: 1204893 (The Pile)

Max Activating Token Index: 783

Text #16

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.9550. Min Act: -0.0000

Data Index: 168702 (The Pile)

Max Activating Token Index: 520

Text #17

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.9154. Min Act: -0.0000

Data Index: 680629 (The Pile)

Max Activating Token Index: 460

Text #18

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.9013. Min Act: -0.0000

Data Index: 1738239 (The Pile)

Max Activating Token Index: 318

Text #19

Max Range: 1.3390. Min Range: -1.3390

Max Act: 0.9478. Min Act: -0.0000

Data Index: 641619 (The Pile)

Max Activating Token Index: 57