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

Dataset: The Pile

Neuron 3081 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: 1.0925. Min Range: -1.0925

Max Act: 1.0739. Min Act: -0.0000

Data Index: 1118299 (The Pile)

Max Activating Token Index: 608

Text #1

Max Range: 1.0925. Min Range: -1.0925

Max Act: 1.0925. Min Act: -0.0000

Data Index: 1300085 (The Pile)

Max Activating Token Index: 137

Text #2

Max Range: 1.0925. Min Range: -1.0925

Max Act: 1.0053. Min Act: -0.0000

Data Index: 836854 (The Pile)

Max Activating Token Index: 885

Text #3

Max Range: 1.0925. Min Range: -1.0925

Max Act: 1.0067. Min Act: -0.0000

Data Index: 614721 (The Pile)

Max Activating Token Index: 603

Text #4

Max Range: 1.0925. Min Range: -1.0925

Max Act: 1.0218. Min Act: -0.0000

Data Index: 1564279 (The Pile)

Max Activating Token Index: 678

Text #5

Max Range: 1.0925. Min Range: -1.0925

Max Act: 1.0004. Min Act: -0.0000

Data Index: 1716539 (The Pile)

Max Activating Token Index: 498

Text #6

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.9716. Min Act: -0.0000

Data Index: 1113398 (The Pile)

Max Activating Token Index: 301

Text #7

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.9888. Min Act: -0.0000

Data Index: 442380 (The Pile)

Max Activating Token Index: 760

Text #8

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.9815. Min Act: -0.0000

Data Index: 592322 (The Pile)

Max Activating Token Index: 640

Text #9

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.9193. Min Act: -0.0000

Data Index: 622357 (The Pile)

Max Activating Token Index: 613

Text #10

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.9406. Min Act: -0.0000

Data Index: 1538008 (The Pile)

Max Activating Token Index: 859

Text #11

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.9457. Min Act: -0.0000

Data Index: 810422 (The Pile)

Max Activating Token Index: 503

Text #12

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.9104. Min Act: -0.0000

Data Index: 100533 (The Pile)

Max Activating Token Index: 689

Text #13

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.9192. Min Act: -0.0000

Data Index: 1383238 (The Pile)

Max Activating Token Index: 564

Text #14

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.8919. Min Act: -0.0000

Data Index: 213726 (The Pile)

Max Activating Token Index: 59

Text #15

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.9123. Min Act: -0.0000

Data Index: 278897 (The Pile)

Max Activating Token Index: 116

Text #16

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.8453. Min Act: -0.0000

Data Index: 758931 (The Pile)

Max Activating Token Index: 1018

Text #17

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.8687. Min Act: -0.0000

Data Index: 1065368 (The Pile)

Max Activating Token Index: 971

Text #18

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.8827. Min Act: -0.0000

Data Index: 447714 (The Pile)

Max Activating Token Index: 623

Text #19

Max Range: 1.0925. Min Range: -1.0925

Max Act: 0.8887. Min Act: -0.0000

Data Index: 328865 (The Pile)

Max Activating Token Index: 34