Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3409 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1441. Min Act: -0.0000

Data Index: 1968419 (The Pile)

Max Activating Token Index: 873

Text #1

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1646. Min Act: -0.0000

Data Index: 310717 (The Pile)

Max Activating Token Index: 845

Text #2

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1466. Min Act: -0.0000

Data Index: 813988 (The Pile)

Max Activating Token Index: 527

Text #3

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1511. Min Act: -0.0000

Data Index: 105937 (The Pile)

Max Activating Token Index: 324

Text #4

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1427. Min Act: -0.0000

Data Index: 963575 (The Pile)

Max Activating Token Index: 434

Text #5

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1266. Min Act: -0.0000

Data Index: 1710696 (The Pile)

Max Activating Token Index: 391

Text #6

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1278. Min Act: -0.0000

Data Index: 207193 (The Pile)

Max Activating Token Index: 918

Text #7

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1304. Min Act: -0.0000

Data Index: 1971208 (The Pile)

Max Activating Token Index: 564

Text #8

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1223. Min Act: -0.0000

Data Index: 523278 (The Pile)

Max Activating Token Index: 1002

Text #9

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1252. Min Act: -0.0000

Data Index: 552485 (The Pile)

Max Activating Token Index: 577

Text #10

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1202. Min Act: -0.0000

Data Index: 734606 (The Pile)

Max Activating Token Index: 817

Text #11

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1276. Min Act: -0.0000

Data Index: 702156 (The Pile)

Max Activating Token Index: 342

Text #12

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1424. Min Act: -0.0000

Data Index: 1231533 (The Pile)

Max Activating Token Index: 830

Text #13

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1185. Min Act: -0.0000

Data Index: 478859 (The Pile)

Max Activating Token Index: 826

Text #14

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1149. Min Act: -0.0000

Data Index: 331813 (The Pile)

Max Activating Token Index: 825

Text #15

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1220. Min Act: -0.0000

Data Index: 1548493 (The Pile)

Max Activating Token Index: 489

Text #16

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1313. Min Act: -0.0001

Data Index: 978454 (The Pile)

Max Activating Token Index: 1018

Text #17

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1206. Min Act: -0.0000

Data Index: 1313122 (The Pile)

Max Activating Token Index: 171

Text #18

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1272. Min Act: -0.0000

Data Index: 1391828 (The Pile)

Max Activating Token Index: 981

Text #19

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1230. Min Act: -0.0000

Data Index: 147174 (The Pile)

Max Activating Token Index: 486