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

Dataset: The Pile

Neuron 3498 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: 1.3505. Min Range: -1.3505

Max Act: 1.3505. Min Act: -0.0000

Data Index: 537525 (The Pile)

Max Activating Token Index: 945

Text #1

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.9841. Min Act: -0.0000

Data Index: 1900550 (The Pile)

Max Activating Token Index: 925

Text #2

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.1454. Min Act: -0.0000

Data Index: 1740593 (The Pile)

Max Activating Token Index: 926

Text #3

Max Range: 1.3505. Min Range: -1.3505

Max Act: 1.0849. Min Act: -0.0000

Data Index: 1491465 (The Pile)

Max Activating Token Index: 622

Text #4

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.9725. Min Act: -0.0000

Data Index: 1595977 (The Pile)

Max Activating Token Index: 84

Text #5

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.9013. Min Act: -0.0000

Data Index: 123063 (The Pile)

Max Activating Token Index: 967

Text #6

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.9590. Min Act: -0.0000

Data Index: 1414586 (The Pile)

Max Activating Token Index: 1018

Text #7

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.9814. Min Act: -0.0000

Data Index: 470049 (The Pile)

Max Activating Token Index: 792

Text #8

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1776943 (The Pile)

Max Activating Token Index: 45

Text #9

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.9657. Min Act: -0.0000

Data Index: 126808 (The Pile)

Max Activating Token Index: 1019

Text #10

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.9362. Min Act: -0.0000

Data Index: 526659 (The Pile)

Max Activating Token Index: 873

Text #11

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.9054. Min Act: -0.0000

Data Index: 1528136 (The Pile)

Max Activating Token Index: 598

Text #12

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.8757. Min Act: -0.0000

Data Index: 1693678 (The Pile)

Max Activating Token Index: 831

Text #13

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.9317. Min Act: -0.0000

Data Index: 1761359 (The Pile)

Max Activating Token Index: 34

Text #14

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.7951. Min Act: -0.0000

Data Index: 1356540 (The Pile)

Max Activating Token Index: 36

Text #15

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.8786. Min Act: -0.0000

Data Index: 1267556 (The Pile)

Max Activating Token Index: 873

Text #16

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.7794. Min Act: -0.0000

Data Index: 653418 (The Pile)

Max Activating Token Index: 861

Text #17

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.9361. Min Act: -0.0000

Data Index: 1197259 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.9230. Min Act: 0.0000

Data Index: 666802 (The Pile)

Max Activating Token Index: 558

Text #19

Max Range: 1.3505. Min Range: -1.3505

Max Act: 0.9148. Min Act: -0.0000

Data Index: 979731 (The Pile)

Max Activating Token Index: 991