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

Dataset: The Pile

Neuron 4567 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.6229. Min Act: -0.0000

Data Index: 1738336 (The Pile)

Max Activating Token Index: 945

Text #1

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5774. Min Act: -0.0000

Data Index: 613225 (The Pile)

Max Activating Token Index: 583

Text #2

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1685373 (The Pile)

Max Activating Token Index: 838

Text #3

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5590. Min Act: -0.0000

Data Index: 1850929 (The Pile)

Max Activating Token Index: 46

Text #4

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.6090. Min Act: -0.0000

Data Index: 1277248 (The Pile)

Max Activating Token Index: 525

Text #5

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5341. Min Act: -0.0000

Data Index: 1730921 (The Pile)

Max Activating Token Index: 706

Text #6

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1322089 (The Pile)

Max Activating Token Index: 78

Text #7

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5477. Min Act: -0.0000

Data Index: 1393106 (The Pile)

Max Activating Token Index: 610

Text #8

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5054. Min Act: -0.0000

Data Index: 1634787 (The Pile)

Max Activating Token Index: 991

Text #9

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5547. Min Act: -0.0000

Data Index: 348418 (The Pile)

Max Activating Token Index: 600

Text #10

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5386. Min Act: -0.0000

Data Index: 1555932 (The Pile)

Max Activating Token Index: 466

Text #11

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4862. Min Act: -0.0000

Data Index: 944764 (The Pile)

Max Activating Token Index: 93

Text #12

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5149. Min Act: -0.0000

Data Index: 1872532 (The Pile)

Max Activating Token Index: 556

Text #13

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5046. Min Act: -0.0000

Data Index: 1721878 (The Pile)

Max Activating Token Index: 1011

Text #14

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4695. Min Act: -0.0000

Data Index: 1163689 (The Pile)

Max Activating Token Index: 814

Text #15

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5124. Min Act: -0.0000

Data Index: 851804 (The Pile)

Max Activating Token Index: 311

Text #16

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.5256. Min Act: -0.0000

Data Index: 849588 (The Pile)

Max Activating Token Index: 809

Text #17

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4886. Min Act: -0.0000

Data Index: 25771 (The Pile)

Max Activating Token Index: 853

Text #18

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4462. Min Act: -0.0000

Data Index: 949588 (The Pile)

Max Activating Token Index: 298

Text #19

Max Range: 0.6229. Min Range: -0.6229

Max Act: 0.4265. Min Act: -0.0000

Data Index: 1153372 (The Pile)

Max Activating Token Index: 524