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

Dataset: The Pile

Neuron 4197 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0789. Min Range: -1.0789

Max Act: 1.0789. Min Act: -0.0000

Data Index: 441525 (The Pile)

Max Activating Token Index: 596

Text #1

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.7984. Min Act: -0.0000

Data Index: 1928161 (The Pile)

Max Activating Token Index: 330

Text #2

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.8409. Min Act: -0.0000

Data Index: 1166404 (The Pile)

Max Activating Token Index: 36

Text #3

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.8447. Min Act: -0.0000

Data Index: 1047997 (The Pile)

Max Activating Token Index: 73

Text #4

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1609162 (The Pile)

Max Activating Token Index: 573

Text #5

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.7997. Min Act: -0.0000

Data Index: 1399070 (The Pile)

Max Activating Token Index: 34

Text #6

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.7985. Min Act: -0.0000

Data Index: 878567 (The Pile)

Max Activating Token Index: 150

Text #7

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1498398 (The Pile)

Max Activating Token Index: 346

Text #8

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.6873. Min Act: -0.0000

Data Index: 1937543 (The Pile)

Max Activating Token Index: 218

Text #9

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.7216. Min Act: -0.0000

Data Index: 181775 (The Pile)

Max Activating Token Index: 456

Text #10

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.7483. Min Act: -0.0000

Data Index: 1346106 (The Pile)

Max Activating Token Index: 726

Text #11

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.6704. Min Act: -0.0000

Data Index: 1237476 (The Pile)

Max Activating Token Index: 927

Text #12

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.7885. Min Act: -0.0000

Data Index: 1279384 (The Pile)

Max Activating Token Index: 532

Text #13

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.7826. Min Act: -0.0000

Data Index: 1991875 (The Pile)

Max Activating Token Index: 344

Text #14

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.7972. Min Act: -0.0000

Data Index: 1921626 (The Pile)

Max Activating Token Index: 104

Text #15

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.7939. Min Act: -0.0000

Data Index: 604992 (The Pile)

Max Activating Token Index: 952

Text #16

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.5784. Min Act: -0.0000

Data Index: 969288 (The Pile)

Max Activating Token Index: 642

Text #17

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.6793. Min Act: -0.0000

Data Index: 1241496 (The Pile)

Max Activating Token Index: 470

Text #18

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.6462. Min Act: -0.0000

Data Index: 1027152 (The Pile)

Max Activating Token Index: 445

Text #19

Max Range: 1.0789. Min Range: -1.0789

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1718883 (The Pile)

Max Activating Token Index: 963