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

Dataset: The Pile

Neuron 2371 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1633. Min Act: -0.0000

Data Index: 1655770 (The Pile)

Max Activating Token Index: 536

Text #1

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1447. Min Act: -0.0000

Data Index: 1548013 (The Pile)

Max Activating Token Index: 684

Text #2

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1609. Min Act: -0.0000

Data Index: 1767606 (The Pile)

Max Activating Token Index: 394

Text #3

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1462. Min Act: -0.0000

Data Index: 1817214 (The Pile)

Max Activating Token Index: 593

Text #4

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1380. Min Act: -0.0000

Data Index: 204424 (The Pile)

Max Activating Token Index: 354

Text #5

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1252. Min Act: -0.0000

Data Index: 1992836 (The Pile)

Max Activating Token Index: 542

Text #6

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1237. Min Act: -0.0000

Data Index: 1440543 (The Pile)

Max Activating Token Index: 697

Text #7

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1294. Min Act: -0.0000

Data Index: 836010 (The Pile)

Max Activating Token Index: 535

Text #8

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1310. Min Act: -0.0000

Data Index: 853792 (The Pile)

Max Activating Token Index: 888

Text #9

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1280. Min Act: -0.0000

Data Index: 808750 (The Pile)

Max Activating Token Index: 764

Text #10

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1265. Min Act: -0.0000

Data Index: 30056 (The Pile)

Max Activating Token Index: 781

Text #11

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1321. Min Act: -0.0000

Data Index: 1503598 (The Pile)

Max Activating Token Index: 619

Text #12

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1854157 (The Pile)

Max Activating Token Index: 696

Text #13

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1177. Min Act: -0.0000

Data Index: 979861 (The Pile)

Max Activating Token Index: 632

Text #14

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1099. Min Act: -0.0000

Data Index: 111622 (The Pile)

Max Activating Token Index: 758

Text #15

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1049. Min Act: -0.0000

Data Index: 491374 (The Pile)

Max Activating Token Index: 557

Text #16

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1079. Min Act: -0.0000

Data Index: 250166 (The Pile)

Max Activating Token Index: 238

Text #17

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.0968. Min Act: -0.0000

Data Index: 857265 (The Pile)

Max Activating Token Index: 497

Text #18

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.0932. Min Act: -0.0000

Data Index: 242261 (The Pile)

Max Activating Token Index: 992

Text #19

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.0955. Min Act: -0.0000

Data Index: 461838 (The Pile)

Max Activating Token Index: 939