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

Dataset: The Pile

Neuron 2742 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 4.0406. Min Range: -4.0406

Max Act: 3.2734. Min Act: -0.0000

Data Index: 766261 (The Pile)

Max Activating Token Index: 831

Text #1

Max Range: 4.0406. Min Range: -4.0406

Max Act: 3.1718. Min Act: -0.0000

Data Index: 1580177 (The Pile)

Max Activating Token Index: 661

Text #2

Max Range: 4.0406. Min Range: -4.0406

Max Act: 4.0406. Min Act: -0.0000

Data Index: 786717 (The Pile)

Max Activating Token Index: 988

Text #3

Max Range: 4.0406. Min Range: -4.0406

Max Act: 3.1745. Min Act: -0.0000

Data Index: 1267264 (The Pile)

Max Activating Token Index: 712

Text #4

Max Range: 4.0406. Min Range: -4.0406

Max Act: 2.9035. Min Act: -0.0000

Data Index: 52570 (The Pile)

Max Activating Token Index: 940

Text #5

Max Range: 4.0406. Min Range: -4.0406

Max Act: 2.9467. Min Act: -0.0000

Data Index: 486883 (The Pile)

Max Activating Token Index: 577

Text #6

Max Range: 4.0406. Min Range: -4.0406

Max Act: 2.9699. Min Act: -0.0000

Data Index: 1004407 (The Pile)

Max Activating Token Index: 457

Text #7

Max Range: 4.0406. Min Range: -4.0406

Max Act: 3.0773. Min Act: -0.0000

Data Index: 851700 (The Pile)

Max Activating Token Index: 741

Text #8

Max Range: 4.0406. Min Range: -4.0406

Max Act: 2.7532. Min Act: -0.0000

Data Index: 761800 (The Pile)

Max Activating Token Index: 259

Text #9

Max Range: 4.0406. Min Range: -4.0406

Max Act: 2.7498. Min Act: -0.0000

Data Index: 1827582 (The Pile)

Max Activating Token Index: 859

Text #10

Max Range: 4.0406. Min Range: -4.0406

Max Act: 2.8443. Min Act: -0.0000

Data Index: 439332 (The Pile)

Max Activating Token Index: 291

Text #11

Max Range: 4.0406. Min Range: -4.0406

Max Act: 2.6647. Min Act: -0.0000

Data Index: 1270404 (The Pile)

Max Activating Token Index: 481

Text #12

Max Range: 4.0406. Min Range: -4.0406

Max Act: 2.8172. Min Act: -0.0000

Data Index: 2015 (The Pile)

Max Activating Token Index: 798

Text #13

Max Range: 4.0406. Min Range: -4.0406

Max Act: 2.9359. Min Act: -0.0000

Data Index: 1451709 (The Pile)

Max Activating Token Index: 987

Text #14

Max Range: 4.0406. Min Range: -4.0406

Max Act: 2.6472. Min Act: -0.0000

Data Index: 1611454 (The Pile)

Max Activating Token Index: 712

Text #15

Max Range: 4.0406. Min Range: -4.0406

Max Act: 2.5918. Min Act: 0.0000

Data Index: 676249 (The Pile)

Max Activating Token Index: 484

Text #16

Max Range: 4.0406. Min Range: -4.0406

Max Act: 2.6851. Min Act: -0.0000

Data Index: 1264639 (The Pile)

Max Activating Token Index: 990

Text #17

Max Range: 4.0406. Min Range: -4.0406

Max Act: 2.4546. Min Act: -0.0000

Data Index: 835508 (The Pile)

Max Activating Token Index: 495

Text #18

Max Range: 4.0406. Min Range: -4.0406

Max Act: 2.5673. Min Act: -0.0000

Data Index: 1227023 (The Pile)

Max Activating Token Index: 675

Text #19

Max Range: 4.0406. Min Range: -4.0406

Max Act: 2.4281. Min Act: -0.0000

Data Index: 1617488 (The Pile)

Max Activating Token Index: 402