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

Dataset: The Pile

Neuron 831 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.7559. Min Act: -0.0000

Data Index: 344082 (The Pile)

Max Activating Token Index: 1013

Text #1

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.8027. Min Act: -0.0000

Data Index: 1203107 (The Pile)

Max Activating Token Index: 105

Text #2

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6549. Min Act: -0.0000

Data Index: 846703 (The Pile)

Max Activating Token Index: 155

Text #3

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.7331. Min Act: -0.0000

Data Index: 1112234 (The Pile)

Max Activating Token Index: 287

Text #4

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6077. Min Act: -0.0000

Data Index: 632691 (The Pile)

Max Activating Token Index: 289

Text #5

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6487. Min Act: -0.0000

Data Index: 1237183 (The Pile)

Max Activating Token Index: 287

Text #6

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.7558. Min Act: -0.0000

Data Index: 99731 (The Pile)

Max Activating Token Index: 426

Text #7

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6428. Min Act: -0.0000

Data Index: 145486 (The Pile)

Max Activating Token Index: 783

Text #8

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6507. Min Act: -0.0000

Data Index: 569802 (The Pile)

Max Activating Token Index: 556

Text #9

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6610. Min Act: -0.0000

Data Index: 1411464 (The Pile)

Max Activating Token Index: 675

Text #10

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6722. Min Act: -0.0000

Data Index: 1477197 (The Pile)

Max Activating Token Index: 359

Text #11

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.5844. Min Act: -0.0000

Data Index: 372029 (The Pile)

Max Activating Token Index: 209

Text #12

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.5470. Min Act: -0.0000

Data Index: 795583 (The Pile)

Max Activating Token Index: 997

Text #13

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6483. Min Act: -0.0000

Data Index: 1635083 (The Pile)

Max Activating Token Index: 487

Text #14

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.5490. Min Act: -0.0000

Data Index: 1278096 (The Pile)

Max Activating Token Index: 687

Text #15

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.5838. Min Act: -0.0000

Data Index: 1708138 (The Pile)

Max Activating Token Index: 167

Text #16

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.6012. Min Act: -0.0000

Data Index: 1091641 (The Pile)

Max Activating Token Index: 352

Text #17

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.5457. Min Act: -0.0000

Data Index: 376196 (The Pile)

Max Activating Token Index: 441

Text #18

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.5911. Min Act: -0.0000

Data Index: 1249102 (The Pile)

Max Activating Token Index: 922

Text #19

Max Range: 0.8027. Min Range: -0.8027

Max Act: 0.5751. Min Act: -0.0000

Data Index: 182473 (The Pile)

Max Activating Token Index: 267