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

Dataset: The Pile

Neuron 1869 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2642. Min Act: -0.0000

Data Index: 1392756 (The Pile)

Max Activating Token Index: 335

Text #1

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2272. Min Act: -0.0000

Data Index: 269796 (The Pile)

Max Activating Token Index: 257

Text #2

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1987. Min Act: -0.0000

Data Index: 1395470 (The Pile)

Max Activating Token Index: 895

Text #3

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1963. Min Act: -0.0000

Data Index: 1198730 (The Pile)

Max Activating Token Index: 282

Text #4

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1865. Min Act: -0.0000

Data Index: 138759 (The Pile)

Max Activating Token Index: 538

Text #5

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1878. Min Act: -0.0000

Data Index: 853029 (The Pile)

Max Activating Token Index: 554

Text #6

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1631. Min Act: -0.0000

Data Index: 400975 (The Pile)

Max Activating Token Index: 984

Text #7

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1756. Min Act: -0.0000

Data Index: 1181551 (The Pile)

Max Activating Token Index: 194

Text #8

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1784. Min Act: -0.0000

Data Index: 885460 (The Pile)

Max Activating Token Index: 926

Text #9

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1906. Min Act: -0.0000

Data Index: 969206 (The Pile)

Max Activating Token Index: 141

Text #10

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1836. Min Act: -0.0000

Data Index: 1848655 (The Pile)

Max Activating Token Index: 249

Text #11

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1981488 (The Pile)

Max Activating Token Index: 919

Text #12

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1674. Min Act: -0.0000

Data Index: 1221404 (The Pile)

Max Activating Token Index: 415

Text #13

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1572. Min Act: -0.0000

Data Index: 738260 (The Pile)

Max Activating Token Index: 346

Text #14

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1627. Min Act: -0.0000

Data Index: 964180 (The Pile)

Max Activating Token Index: 112

Text #15

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1659. Min Act: -0.0000

Data Index: 1759562 (The Pile)

Max Activating Token Index: 253

Text #16

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1561. Min Act: -0.0000

Data Index: 170847 (The Pile)

Max Activating Token Index: 685

Text #17

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1686. Min Act: -0.0000

Data Index: 1538736 (The Pile)

Max Activating Token Index: 988

Text #18

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1528. Min Act: -0.0000

Data Index: 450078 (The Pile)

Max Activating Token Index: 206

Text #19

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1516. Min Act: -0.0000

Data Index: 1979429 (The Pile)

Max Activating Token Index: 744