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

Dataset: The Pile

Neuron 791 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.9569. Min Act: -0.0000

Data Index: 1029951 (The Pile)

Max Activating Token Index: 519

Text #1

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.8220. Min Act: -0.0000

Data Index: 1975426 (The Pile)

Max Activating Token Index: 992

Text #2

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.8185. Min Act: -0.0000

Data Index: 30756 (The Pile)

Max Activating Token Index: 910

Text #3

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.8613. Min Act: -0.0000

Data Index: 1978800 (The Pile)

Max Activating Token Index: 909

Text #4

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.8591. Min Act: -0.0000

Data Index: 597476 (The Pile)

Max Activating Token Index: 762

Text #5

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.8208. Min Act: -0.0000

Data Index: 1940679 (The Pile)

Max Activating Token Index: 471

Text #6

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.8497. Min Act: -0.0000

Data Index: 591852 (The Pile)

Max Activating Token Index: 257

Text #7

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1448964 (The Pile)

Max Activating Token Index: 678

Text #8

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.7756. Min Act: -0.0000

Data Index: 1685357 (The Pile)

Max Activating Token Index: 415

Text #9

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.8484. Min Act: -0.0000

Data Index: 1885197 (The Pile)

Max Activating Token Index: 211

Text #10

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.8444. Min Act: -0.0000

Data Index: 1574239 (The Pile)

Max Activating Token Index: 787

Text #11

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.7840. Min Act: -0.0000

Data Index: 1739928 (The Pile)

Max Activating Token Index: 895

Text #12

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.7828. Min Act: -0.0000

Data Index: 611173 (The Pile)

Max Activating Token Index: 119

Text #13

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.7332. Min Act: -0.0000

Data Index: 1581081 (The Pile)

Max Activating Token Index: 870

Text #14

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.8175. Min Act: -0.0000

Data Index: 482366 (The Pile)

Max Activating Token Index: 422

Text #15

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.7608. Min Act: -0.0000

Data Index: 1550431 (The Pile)

Max Activating Token Index: 908

Text #16

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.7412. Min Act: -0.0000

Data Index: 22494 (The Pile)

Max Activating Token Index: 388

Text #17

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.8029. Min Act: -0.0000

Data Index: 1484203 (The Pile)

Max Activating Token Index: 331

Text #18

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.7774. Min Act: -0.0000

Data Index: 326504 (The Pile)

Max Activating Token Index: 248

Text #19

Max Range: 0.9569. Min Range: -0.9569

Max Act: 0.7214. Min Act: -0.0000

Data Index: 845976 (The Pile)

Max Activating Token Index: 436