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

Dataset: The Pile

Neuron 118 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: 1.0893. Min Range: -1.0893

Max Act: 1.0732. Min Act: -0.0000

Data Index: 1055261 (The Pile)

Max Activating Token Index: 90

Text #1

Max Range: 1.0893. Min Range: -1.0893

Max Act: 1.0277. Min Act: -0.0000

Data Index: 1482419 (The Pile)

Max Activating Token Index: 290

Text #2

Max Range: 1.0893. Min Range: -1.0893

Max Act: 1.0550. Min Act: -0.0000

Data Index: 1685448 (The Pile)

Max Activating Token Index: 264

Text #3

Max Range: 1.0893. Min Range: -1.0893

Max Act: 1.0455. Min Act: -0.0000

Data Index: 1692186 (The Pile)

Max Activating Token Index: 1020

Text #4

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9991. Min Act: -0.0000

Data Index: 381094 (The Pile)

Max Activating Token Index: 867

Text #5

Max Range: 1.0893. Min Range: -1.0893

Max Act: 1.0893. Min Act: -0.0000

Data Index: 1222604 (The Pile)

Max Activating Token Index: 782

Text #6

Max Range: 1.0893. Min Range: -1.0893

Max Act: 1.0543. Min Act: -0.0000

Data Index: 1320168 (The Pile)

Max Activating Token Index: 191

Text #7

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9571. Min Act: -0.0000

Data Index: 1297760 (The Pile)

Max Activating Token Index: 460

Text #8

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9625. Min Act: -0.0000

Data Index: 765412 (The Pile)

Max Activating Token Index: 508

Text #9

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9469. Min Act: -0.0000

Data Index: 66931 (The Pile)

Max Activating Token Index: 797

Text #10

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9540. Min Act: -0.0000

Data Index: 1353182 (The Pile)

Max Activating Token Index: 462

Text #11

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8772. Min Act: -0.0000

Data Index: 385646 (The Pile)

Max Activating Token Index: 438

Text #12

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8795. Min Act: -0.0000

Data Index: 260289 (The Pile)

Max Activating Token Index: 323

Text #13

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9505. Min Act: -0.0000

Data Index: 203499 (The Pile)

Max Activating Token Index: 854

Text #14

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9032. Min Act: -0.0000

Data Index: 297641 (The Pile)

Max Activating Token Index: 450

Text #15

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.9096. Min Act: -0.0000

Data Index: 1579506 (The Pile)

Max Activating Token Index: 846

Text #16

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8929. Min Act: -0.0000

Data Index: 295186 (The Pile)

Max Activating Token Index: 666

Text #17

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8076. Min Act: -0.0000

Data Index: 1764121 (The Pile)

Max Activating Token Index: 605

Text #18

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8842. Min Act: -0.0000

Data Index: 316036 (The Pile)

Max Activating Token Index: 819

Text #19

Max Range: 1.0893. Min Range: -1.0893

Max Act: 0.8778. Min Act: -0.0000

Data Index: 1007993 (The Pile)

Max Activating Token Index: 325