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

Dataset: The Pile

Neuron 3379 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: 1.9523. Min Range: -1.9523

Max Act: 1.6698. Min Act: -0.0000

Data Index: 1863935 (The Pile)

Max Activating Token Index: 283

Text #1

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.7932. Min Act: -0.0000

Data Index: 92162 (The Pile)

Max Activating Token Index: 719

Text #2

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.5983. Min Act: -0.0000

Data Index: 347836 (The Pile)

Max Activating Token Index: 676

Text #3

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.9523. Min Act: -0.0000

Data Index: 1059272 (The Pile)

Max Activating Token Index: 401

Text #4

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.6909. Min Act: -0.0000

Data Index: 1997246 (The Pile)

Max Activating Token Index: 697

Text #5

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.6460. Min Act: -0.0000

Data Index: 1532435 (The Pile)

Max Activating Token Index: 557

Text #6

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.6415. Min Act: -0.0000

Data Index: 543440 (The Pile)

Max Activating Token Index: 502

Text #7

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.5323. Min Act: -0.0000

Data Index: 63003 (The Pile)

Max Activating Token Index: 516

Text #8

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.6157. Min Act: -0.0000

Data Index: 1845103 (The Pile)

Max Activating Token Index: 244

Text #9

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.6023. Min Act: -0.0000

Data Index: 1280129 (The Pile)

Max Activating Token Index: 417

Text #10

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.6928. Min Act: -0.0000

Data Index: 373322 (The Pile)

Max Activating Token Index: 165

Text #11

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.5970. Min Act: -0.0000

Data Index: 1851593 (The Pile)

Max Activating Token Index: 188

Text #12

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.5701. Min Act: -0.0000

Data Index: 1777764 (The Pile)

Max Activating Token Index: 621

Text #13

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.6498. Min Act: -0.0000

Data Index: 401738 (The Pile)

Max Activating Token Index: 462

Text #14

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.5213. Min Act: -0.0000

Data Index: 1268516 (The Pile)

Max Activating Token Index: 409

Text #15

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.5642. Min Act: -0.0000

Data Index: 820510 (The Pile)

Max Activating Token Index: 111

Text #16

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.6079. Min Act: -0.0000

Data Index: 1338567 (The Pile)

Max Activating Token Index: 111

Text #17

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.4473. Min Act: -0.0000

Data Index: 1836402 (The Pile)

Max Activating Token Index: 333

Text #18

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.5171. Min Act: -0.0000

Data Index: 1846206 (The Pile)

Max Activating Token Index: 487

Text #19

Max Range: 1.9523. Min Range: -1.9523

Max Act: 1.4652. Min Act: -0.0000

Data Index: 987747 (The Pile)

Max Activating Token Index: 309