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

Dataset: The Pile

Neuron 4431 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: 1.2040. Min Range: -1.2040

Max Act: 1.2040. Min Act: -0.0000

Data Index: 1044433 (The Pile)

Max Activating Token Index: 972

Text #1

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.9126. Min Act: -0.0000

Data Index: 1897407 (The Pile)

Max Activating Token Index: 203

Text #2

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.7540. Min Act: -0.0000

Data Index: 1612692 (The Pile)

Max Activating Token Index: 278

Text #3

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.9034. Min Act: -0.0000

Data Index: 176206 (The Pile)

Max Activating Token Index: 168

Text #4

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.7499. Min Act: -0.0000

Data Index: 1158788 (The Pile)

Max Activating Token Index: 539

Text #5

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.8297. Min Act: -0.0000

Data Index: 644424 (The Pile)

Max Activating Token Index: 356

Text #6

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1530400 (The Pile)

Max Activating Token Index: 155

Text #7

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.8138. Min Act: -0.0000

Data Index: 1953067 (The Pile)

Max Activating Token Index: 251

Text #8

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.7959. Min Act: -0.0000

Data Index: 770877 (The Pile)

Max Activating Token Index: 605

Text #9

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.8725. Min Act: -0.0000

Data Index: 1915415 (The Pile)

Max Activating Token Index: 185

Text #10

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.8247. Min Act: -0.0000

Data Index: 676249 (The Pile)

Max Activating Token Index: 23

Text #11

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.7206. Min Act: -0.0000

Data Index: 849846 (The Pile)

Max Activating Token Index: 33

Text #12

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.8009. Min Act: -0.0000

Data Index: 84383 (The Pile)

Max Activating Token Index: 665

Text #13

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.7551. Min Act: 0.0000

Data Index: 1438582 (The Pile)

Max Activating Token Index: 768

Text #14

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.7575. Min Act: -0.0000

Data Index: 1556124 (The Pile)

Max Activating Token Index: 655

Text #15

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.8006. Min Act: -0.0000

Data Index: 1231988 (The Pile)

Max Activating Token Index: 757

Text #16

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.8010. Min Act: -0.0000

Data Index: 1496446 (The Pile)

Max Activating Token Index: 358

Text #17

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.8450. Min Act: -0.0000

Data Index: 1040037 (The Pile)

Max Activating Token Index: 798

Text #18

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.7493. Min Act: -0.0000

Data Index: 576896 (The Pile)

Max Activating Token Index: 255

Text #19

Max Range: 1.2040. Min Range: -1.2040

Max Act: 0.7706. Min Act: -0.0000

Data Index: 1768836 (The Pile)

Max Activating Token Index: 720