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

Dataset: The Pile

Neuron 4449 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1457. Min Act: -0.0000

Data Index: 97723 (The Pile)

Max Activating Token Index: 386

Text #1

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1921490 (The Pile)

Max Activating Token Index: 464

Text #2

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1015. Min Act: -0.0000

Data Index: 41365 (The Pile)

Max Activating Token Index: 527

Text #3

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1052. Min Act: -0.0000

Data Index: 1475380 (The Pile)

Max Activating Token Index: 623

Text #4

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1073. Min Act: -0.0000

Data Index: 719946 (The Pile)

Max Activating Token Index: 482

Text #5

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0898. Min Act: -0.0000

Data Index: 725815 (The Pile)

Max Activating Token Index: 143

Text #6

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0909. Min Act: -0.0000

Data Index: 1605827 (The Pile)

Max Activating Token Index: 306

Text #7

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1931363 (The Pile)

Max Activating Token Index: 711

Text #8

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0844. Min Act: -0.0000

Data Index: 1505351 (The Pile)

Max Activating Token Index: 251

Text #9

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0849. Min Act: -0.0000

Data Index: 153274 (The Pile)

Max Activating Token Index: 54

Text #10

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0825. Min Act: -0.0000

Data Index: 805805 (The Pile)

Max Activating Token Index: 641

Text #11

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0844. Min Act: -0.0000

Data Index: 717381 (The Pile)

Max Activating Token Index: 67

Text #12

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0821. Min Act: -0.0000

Data Index: 1979795 (The Pile)

Max Activating Token Index: 551

Text #13

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0846. Min Act: -0.0000

Data Index: 1941131 (The Pile)

Max Activating Token Index: 699

Text #14

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0776. Min Act: -0.0000

Data Index: 1878288 (The Pile)

Max Activating Token Index: 111

Text #15

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0749. Min Act: -0.0000

Data Index: 1836147 (The Pile)

Max Activating Token Index: 847

Text #16

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0745. Min Act: -0.0000

Data Index: 1568485 (The Pile)

Max Activating Token Index: 546

Text #17

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0770. Min Act: -0.0000

Data Index: 568687 (The Pile)

Max Activating Token Index: 743

Text #18

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0756. Min Act: -0.0000

Data Index: 1185776 (The Pile)

Max Activating Token Index: 497

Text #19

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0760. Min Act: -0.0000

Data Index: 1496826 (The Pile)

Max Activating Token Index: 520