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

Dataset: The Pile

Neuron 57 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: 0.5004. Min Range: -0.5004

Max Act: 0.5004. Min Act: -0.0000

Data Index: 1273516 (The Pile)

Max Activating Token Index: 271

Text #1

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1242224 (The Pile)

Max Activating Token Index: 455

Text #2

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4625. Min Act: -0.0000

Data Index: 1373765 (The Pile)

Max Activating Token Index: 684

Text #3

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1509754 (The Pile)

Max Activating Token Index: 454

Text #4

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1965073 (The Pile)

Max Activating Token Index: 308

Text #5

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.4120. Min Act: -0.0000

Data Index: 618974 (The Pile)

Max Activating Token Index: 962

Text #6

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1320323 (The Pile)

Max Activating Token Index: 342

Text #7

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3769. Min Act: -0.0000

Data Index: 1530052 (The Pile)

Max Activating Token Index: 626

Text #8

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3893. Min Act: -0.0000

Data Index: 975822 (The Pile)

Max Activating Token Index: 192

Text #9

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3808. Min Act: -0.0000

Data Index: 1935371 (The Pile)

Max Activating Token Index: 234

Text #10

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3789. Min Act: -0.0000

Data Index: 549337 (The Pile)

Max Activating Token Index: 311

Text #11

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3720. Min Act: -0.0000

Data Index: 213374 (The Pile)

Max Activating Token Index: 88

Text #12

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3833. Min Act: -0.0000

Data Index: 403589 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3550. Min Act: -0.0000

Data Index: 362872 (The Pile)

Max Activating Token Index: 374

Text #14

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3628. Min Act: -0.0000

Data Index: 667328 (The Pile)

Max Activating Token Index: 523

Text #15

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3738. Min Act: -0.0000

Data Index: 499429 (The Pile)

Max Activating Token Index: 450

Text #16

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3576. Min Act: -0.0000

Data Index: 260314 (The Pile)

Max Activating Token Index: 488

Text #17

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3383. Min Act: -0.0000

Data Index: 573310 (The Pile)

Max Activating Token Index: 743

Text #18

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3653. Min Act: -0.0000

Data Index: 992133 (The Pile)

Max Activating Token Index: 268

Text #19

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3334. Min Act: -0.0000

Data Index: 1278502 (The Pile)

Max Activating Token Index: 617