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

Dataset: The Pile

Neuron 1997 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: 3.0955. Min Range: -3.0955

Max Act: 3.0955. Min Act: -0.0000

Data Index: 587380 (The Pile)

Max Activating Token Index: 562

Text #1

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.9864. Min Act: -0.0000

Data Index: 646607 (The Pile)

Max Activating Token Index: 419

Text #2

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.3193. Min Act: -0.0000

Data Index: 1065895 (The Pile)

Max Activating Token Index: 855

Text #3

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.2883. Min Act: -0.0000

Data Index: 219851 (The Pile)

Max Activating Token Index: 208

Text #4

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.2517. Min Act: -0.0000

Data Index: 962386 (The Pile)

Max Activating Token Index: 942

Text #5

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.3184. Min Act: -0.0000

Data Index: 175715 (The Pile)

Max Activating Token Index: 325

Text #6

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.0132. Min Act: -0.0000

Data Index: 627666 (The Pile)

Max Activating Token Index: 709

Text #7

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.1850. Min Act: -0.0000

Data Index: 657890 (The Pile)

Max Activating Token Index: 20

Text #8

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.1068. Min Act: -0.0000

Data Index: 1011422 (The Pile)

Max Activating Token Index: 580

Text #9

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.1572. Min Act: -0.0000

Data Index: 1550812 (The Pile)

Max Activating Token Index: 135

Text #10

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.0275. Min Act: -0.0000

Data Index: 930591 (The Pile)

Max Activating Token Index: 912

Text #11

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.0251. Min Act: -0.0000

Data Index: 1577510 (The Pile)

Max Activating Token Index: 248

Text #12

Max Range: 3.0955. Min Range: -3.0955

Max Act: 1.9115. Min Act: -0.0000

Data Index: 1086138 (The Pile)

Max Activating Token Index: 51

Text #13

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.0051. Min Act: -0.0000

Data Index: 758006 (The Pile)

Max Activating Token Index: 483

Text #14

Max Range: 3.0955. Min Range: -3.0955

Max Act: 2.1897. Min Act: -0.0000

Data Index: 822401 (The Pile)

Max Activating Token Index: 617

Text #15

Max Range: 3.0955. Min Range: -3.0955

Max Act: 1.9721. Min Act: -0.0000

Data Index: 1689087 (The Pile)

Max Activating Token Index: 745

Text #16

Max Range: 3.0955. Min Range: -3.0955

Max Act: 1.8456. Min Act: -0.0000

Data Index: 1486594 (The Pile)

Max Activating Token Index: 530

Text #17

Max Range: 3.0955. Min Range: -3.0955

Max Act: 1.8367. Min Act: -0.0000

Data Index: 1569474 (The Pile)

Max Activating Token Index: 503

Text #18

Max Range: 3.0955. Min Range: -3.0955

Max Act: 1.9543. Min Act: -0.0000

Data Index: 1957314 (The Pile)

Max Activating Token Index: 779

Text #19

Max Range: 3.0955. Min Range: -3.0955

Max Act: 1.7283. Min Act: -0.0000

Data Index: 1265674 (The Pile)

Max Activating Token Index: 134