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

Dataset: The Pile

Neuron 4021 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: 0.2638. Min Range: -0.2638

Max Act: 0.2638. Min Act: -0.0000

Data Index: 45367 (The Pile)

Max Activating Token Index: 511

Text #1

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2275. Min Act: -0.0000

Data Index: 263148 (The Pile)

Max Activating Token Index: 208

Text #2

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2260. Min Act: -0.0000

Data Index: 1039373 (The Pile)

Max Activating Token Index: 399

Text #3

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2580. Min Act: -0.0000

Data Index: 1397126 (The Pile)

Max Activating Token Index: 103

Text #4

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2135. Min Act: -0.0000

Data Index: 1239833 (The Pile)

Max Activating Token Index: 383

Text #5

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1368425 (The Pile)

Max Activating Token Index: 823

Text #6

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2259. Min Act: -0.0000

Data Index: 826544 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2420. Min Act: -0.0000

Data Index: 1295393 (The Pile)

Max Activating Token Index: 162

Text #8

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2191. Min Act: -0.0000

Data Index: 959145 (The Pile)

Max Activating Token Index: 940

Text #9

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1820. Min Act: -0.0000

Data Index: 336128 (The Pile)

Max Activating Token Index: 324

Text #10

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1774. Min Act: -0.0000

Data Index: 690717 (The Pile)

Max Activating Token Index: 48

Text #11

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1521. Min Act: -0.0000

Data Index: 372595 (The Pile)

Max Activating Token Index: 207

Text #12

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1877. Min Act: -0.0000

Data Index: 1275047 (The Pile)

Max Activating Token Index: 865

Text #13

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1723. Min Act: -0.0000

Data Index: 1447754 (The Pile)

Max Activating Token Index: 134

Text #14

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1741. Min Act: -0.0000

Data Index: 1517388 (The Pile)

Max Activating Token Index: 971

Text #15

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1406470 (The Pile)

Max Activating Token Index: 199

Text #16

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1585. Min Act: -0.0000

Data Index: 119410 (The Pile)

Max Activating Token Index: 596

Text #17

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.2332. Min Act: -0.0000

Data Index: 862684 (The Pile)

Max Activating Token Index: 923

Text #18

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1727. Min Act: -0.0000

Data Index: 1376783 (The Pile)

Max Activating Token Index: 337

Text #19

Max Range: 0.2638. Min Range: -0.2638

Max Act: 0.1513. Min Act: -0.0000

Data Index: 1138042 (The Pile)

Max Activating Token Index: 201