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

Dataset: The Pile

Neuron 2614 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: 0.6286. Min Range: -0.6286

Max Act: 0.6286. Min Act: -0.0000

Data Index: 1980952 (The Pile)

Max Activating Token Index: 750

Text #1

Max Range: 0.6286. Min Range: -0.6286

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1281128 (The Pile)

Max Activating Token Index: 617

Text #2

Max Range: 0.6286. Min Range: -0.6286

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1942623 (The Pile)

Max Activating Token Index: 955

Text #3

Max Range: 0.6286. Min Range: -0.6286

Max Act: 0.5754. Min Act: 0.0000

Data Index: 1830348 (The Pile)

Max Activating Token Index: 491

Text #4

Max Range: 0.6286. Min Range: -0.6286

Max Act: 0.5514. Min Act: 0.0000

Data Index: 902011 (The Pile)

Max Activating Token Index: 562

Text #5

Max Range: 0.6286. Min Range: -0.6286

Max Act: 0.5240. Min Act: -0.0000

Data Index: 1227236 (The Pile)

Max Activating Token Index: 242

Text #6

Max Range: 0.6286. Min Range: -0.6286

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1980186 (The Pile)

Max Activating Token Index: 673

Text #7

Max Range: 0.6286. Min Range: -0.6286

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1936683 (The Pile)

Max Activating Token Index: 679

Text #8

Max Range: 0.6286. Min Range: -0.6286

Max Act: 0.4783. Min Act: -0.0000

Data Index: 1640551 (The Pile)

Max Activating Token Index: 214

Text #9

Max Range: 0.6286. Min Range: -0.6286

Max Act: 0.4640. Min Act: 0.0000

Data Index: 124009 (The Pile)

Max Activating Token Index: 65

Text #10

Max Range: 0.6286. Min Range: -0.6286

Max Act: 0.4487. Min Act: -0.0000

Data Index: 1646110 (The Pile)

Max Activating Token Index: 603

Text #11

Max Range: 0.6286. Min Range: -0.6286

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1502397 (The Pile)

Max Activating Token Index: 918

Text #12

Max Range: 0.6286. Min Range: -0.6286

Max Act: 0.4847. Min Act: -0.0000

Data Index: 1146590 (The Pile)

Max Activating Token Index: 639

Text #13

Max Range: 0.6286. Min Range: -0.6286

Max Act: 0.4529. Min Act: 0.0000

Data Index: 1420205 (The Pile)

Max Activating Token Index: 738

Text #14

Max Range: 0.6286. Min Range: -0.6286

Max Act: 0.4585. Min Act: -0.0000

Data Index: 1064191 (The Pile)

Max Activating Token Index: 21

Text #15

Max Range: 0.6286. Min Range: -0.6286

Max Act: 0.4756. Min Act: -0.0000

Data Index: 852440 (The Pile)

Max Activating Token Index: 915

Text #16

Max Range: 0.6286. Min Range: -0.6286

Max Act: 0.4544. Min Act: -0.0000

Data Index: 1557600 (The Pile)

Max Activating Token Index: 309

Text #17

Max Range: 0.6286. Min Range: -0.6286

Max Act: 0.4643. Min Act: 0.0000

Data Index: 62345 (The Pile)

Max Activating Token Index: 604

Text #18

Max Range: 0.6286. Min Range: -0.6286

Max Act: 0.4452. Min Act: -0.0000

Data Index: 41604 (The Pile)

Max Activating Token Index: 959

Text #19

Max Range: 0.6286. Min Range: -0.6286

Max Act: 0.4720. Min Act: -0.0000

Data Index: 1889106 (The Pile)

Max Activating Token Index: 791