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

Dataset: The Pile

Neuron 3338 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: 5.3887. Min Range: -5.3887

Max Act: 5.3887. Min Act: -0.0000

Data Index: 201350 (The Pile)

Max Activating Token Index: 751

Text #1

Max Range: 5.3887. Min Range: -5.3887

Max Act: 2.6454. Min Act: -0.0000

Data Index: 1033067 (The Pile)

Max Activating Token Index: 552

Text #2

Max Range: 5.3887. Min Range: -5.3887

Max Act: 2.6891. Min Act: -0.0000

Data Index: 54777 (The Pile)

Max Activating Token Index: 824

Text #3

Max Range: 5.3887. Min Range: -5.3887

Max Act: 3.1531. Min Act: -0.0000

Data Index: 1160389 (The Pile)

Max Activating Token Index: 877

Text #4

Max Range: 5.3887. Min Range: -5.3887

Max Act: 2.4227. Min Act: -0.0000

Data Index: 779973 (The Pile)

Max Activating Token Index: 635

Text #5

Max Range: 5.3887. Min Range: -5.3887

Max Act: 2.1797. Min Act: -0.0000

Data Index: 1502619 (The Pile)

Max Activating Token Index: 179

Text #6

Max Range: 5.3887. Min Range: -5.3887

Max Act: 2.1249. Min Act: -0.0000

Data Index: 1434676 (The Pile)

Max Activating Token Index: 627

Text #7

Max Range: 5.3887. Min Range: -5.3887

Max Act: 2.0278. Min Act: -0.0000

Data Index: 1572615 (The Pile)

Max Activating Token Index: 594

Text #8

Max Range: 5.3887. Min Range: -5.3887

Max Act: 2.5102. Min Act: -0.0000

Data Index: 1858189 (The Pile)

Max Activating Token Index: 932

Text #9

Max Range: 5.3887. Min Range: -5.3887

Max Act: 1.7084. Min Act: -0.0000

Data Index: 762445 (The Pile)

Max Activating Token Index: 259

Text #10

Max Range: 5.3887. Min Range: -5.3887

Max Act: 1.6047. Min Act: -0.0000

Data Index: 741938 (The Pile)

Max Activating Token Index: 58

Text #11

Max Range: 5.3887. Min Range: -5.3887

Max Act: 1.4849. Min Act: -0.0000

Data Index: 1807014 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 5.3887. Min Range: -5.3887

Max Act: 1.7132. Min Act: -0.0000

Data Index: 326441 (The Pile)

Max Activating Token Index: 106

Text #13

Max Range: 5.3887. Min Range: -5.3887

Max Act: 1.5106. Min Act: -0.0000

Data Index: 1848381 (The Pile)

Max Activating Token Index: 169

Text #14

Max Range: 5.3887. Min Range: -5.3887

Max Act: 1.5053. Min Act: -0.0000

Data Index: 15846 (The Pile)

Max Activating Token Index: 171

Text #15

Max Range: 5.3887. Min Range: -5.3887

Max Act: 1.5476. Min Act: -0.0000

Data Index: 1809400 (The Pile)

Max Activating Token Index: 226

Text #16

Max Range: 5.3887. Min Range: -5.3887

Max Act: 1.5900. Min Act: -0.0000

Data Index: 1145492 (The Pile)

Max Activating Token Index: 558

Text #17

Max Range: 5.3887. Min Range: -5.3887

Max Act: 1.4053. Min Act: -0.0000

Data Index: 1921845 (The Pile)

Max Activating Token Index: 448

Text #18

Max Range: 5.3887. Min Range: -5.3887

Max Act: 1.3872. Min Act: -0.0000

Data Index: 688603 (The Pile)

Max Activating Token Index: 643

Text #19

Max Range: 5.3887. Min Range: -5.3887

Max Act: 1.4732. Min Act: -0.0000

Data Index: 784323 (The Pile)

Max Activating Token Index: 430