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

Dataset: The Pile

Neuron 2517 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2356. Min Range: -1.2356

Max Act: 1.2356. Min Act: -0.0000

Data Index: 114690 (The Pile)

Max Activating Token Index: 752

Text #1

Max Range: 1.2356. Min Range: -1.2356

Max Act: 1.0108. Min Act: -0.0000

Data Index: 122196 (The Pile)

Max Activating Token Index: 197

Text #2

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.9295. Min Act: -0.0000

Data Index: 1943929 (The Pile)

Max Activating Token Index: 536

Text #3

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.9193. Min Act: -0.0000

Data Index: 218391 (The Pile)

Max Activating Token Index: 392

Text #4

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.7509. Min Act: -0.0000

Data Index: 1952510 (The Pile)

Max Activating Token Index: 248

Text #5

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.7242. Min Act: -0.0000

Data Index: 1312098 (The Pile)

Max Activating Token Index: 749

Text #6

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.7570. Min Act: -0.0000

Data Index: 1294809 (The Pile)

Max Activating Token Index: 815

Text #7

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.7200. Min Act: -0.0000

Data Index: 587770 (The Pile)

Max Activating Token Index: 474

Text #8

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.7952. Min Act: -0.0000

Data Index: 1016051 (The Pile)

Max Activating Token Index: 299

Text #9

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.7546. Min Act: -0.0000

Data Index: 1308919 (The Pile)

Max Activating Token Index: 155

Text #10

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.7468. Min Act: -0.0000

Data Index: 424785 (The Pile)

Max Activating Token Index: 111

Text #11

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.7972. Min Act: -0.0000

Data Index: 233802 (The Pile)

Max Activating Token Index: 118

Text #12

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.7147. Min Act: -0.0000

Data Index: 1358896 (The Pile)

Max Activating Token Index: 167

Text #13

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.7285. Min Act: -0.0000

Data Index: 457031 (The Pile)

Max Activating Token Index: 977

Text #14

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1308353 (The Pile)

Max Activating Token Index: 868

Text #15

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.6879. Min Act: -0.0000

Data Index: 1802431 (The Pile)

Max Activating Token Index: 1004

Text #16

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.6654. Min Act: -0.0000

Data Index: 1987527 (The Pile)

Max Activating Token Index: 518

Text #17

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.5859. Min Act: -0.0000

Data Index: 565881 (The Pile)

Max Activating Token Index: 840

Text #18

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.6829. Min Act: -0.0000

Data Index: 334520 (The Pile)

Max Activating Token Index: 538

Text #19

Max Range: 1.2356. Min Range: -1.2356

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1620871 (The Pile)

Max Activating Token Index: 146