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

Dataset: The Pile

Neuron 3143 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.7471. Min Act: -0.0000

Data Index: 1985066 (The Pile)

Max Activating Token Index: 301

Text #1

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.6589. Min Act: -0.0000

Data Index: 268524 (The Pile)

Max Activating Token Index: 960

Text #2

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.5980. Min Act: -0.0000

Data Index: 65006 (The Pile)

Max Activating Token Index: 455

Text #3

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.5760. Min Act: -0.0000

Data Index: 600041 (The Pile)

Max Activating Token Index: 176

Text #4

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.5513. Min Act: -0.0000

Data Index: 1241791 (The Pile)

Max Activating Token Index: 175

Text #5

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.5468. Min Act: -0.0000

Data Index: 264561 (The Pile)

Max Activating Token Index: 688

Text #6

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.5371. Min Act: -0.0000

Data Index: 609690 (The Pile)

Max Activating Token Index: 678

Text #7

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1942069 (The Pile)

Max Activating Token Index: 873

Text #8

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.5249. Min Act: -0.0000

Data Index: 1570022 (The Pile)

Max Activating Token Index: 765

Text #9

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.5249. Min Act: -0.0000

Data Index: 605478 (The Pile)

Max Activating Token Index: 298

Text #10

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.4602. Min Act: -0.0000

Data Index: 1886451 (The Pile)

Max Activating Token Index: 806

Text #11

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.4798. Min Act: -0.0000

Data Index: 490073 (The Pile)

Max Activating Token Index: 665

Text #12

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.5105. Min Act: -0.0000

Data Index: 188242 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.5097. Min Act: -0.0000

Data Index: 864259 (The Pile)

Max Activating Token Index: 115

Text #14

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.5041. Min Act: -0.0000

Data Index: 1172253 (The Pile)

Max Activating Token Index: 701

Text #15

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.4907. Min Act: -0.0000

Data Index: 63869 (The Pile)

Max Activating Token Index: 398

Text #16

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.4718. Min Act: -0.0000

Data Index: 991958 (The Pile)

Max Activating Token Index: 713

Text #17

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.4718. Min Act: -0.0000

Data Index: 197460 (The Pile)

Max Activating Token Index: 514

Text #18

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1286249 (The Pile)

Max Activating Token Index: 28

Text #19

Max Range: 0.7471. Min Range: -0.7471

Max Act: 0.4845. Min Act: -0.0000

Data Index: 676607 (The Pile)

Max Activating Token Index: 668