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

Dataset: The Pile

Neuron 2026 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: 0.1686. Min Range: -0.1686

Max Act: 0.1686. Min Act: -0.0000

Data Index: 1014738 (The Pile)

Max Activating Token Index: 294

Text #1

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1409537 (The Pile)

Max Activating Token Index: 949

Text #2

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1613. Min Act: -0.0000

Data Index: 1180066 (The Pile)

Max Activating Token Index: 419

Text #3

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1358. Min Act: -0.0000

Data Index: 117505 (The Pile)

Max Activating Token Index: 183

Text #4

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1473. Min Act: -0.0000

Data Index: 1671372 (The Pile)

Max Activating Token Index: 869

Text #5

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1265. Min Act: -0.0000

Data Index: 33778 (The Pile)

Max Activating Token Index: 687

Text #6

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1196. Min Act: -0.0000

Data Index: 1712418 (The Pile)

Max Activating Token Index: 129

Text #7

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1283. Min Act: -0.0000

Data Index: 586777 (The Pile)

Max Activating Token Index: 242

Text #8

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1337. Min Act: -0.0000

Data Index: 804602 (The Pile)

Max Activating Token Index: 694

Text #9

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1238. Min Act: -0.0000

Data Index: 1469485 (The Pile)

Max Activating Token Index: 214

Text #10

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1220. Min Act: -0.0000

Data Index: 1833338 (The Pile)

Max Activating Token Index: 823

Text #11

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1310. Min Act: -0.0000

Data Index: 1253971 (The Pile)

Max Activating Token Index: 872

Text #12

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1339. Min Act: -0.0000

Data Index: 631950 (The Pile)

Max Activating Token Index: 904

Text #13

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1353. Min Act: -0.0000

Data Index: 1370883 (The Pile)

Max Activating Token Index: 746

Text #14

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1316. Min Act: -0.0000

Data Index: 432149 (The Pile)

Max Activating Token Index: 79

Text #15

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1241. Min Act: -0.0000

Data Index: 784622 (The Pile)

Max Activating Token Index: 934

Text #16

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1175. Min Act: -0.0000

Data Index: 1023058 (The Pile)

Max Activating Token Index: 917

Text #17

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1266. Min Act: -0.0000

Data Index: 395514 (The Pile)

Max Activating Token Index: 821

Text #18

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1193. Min Act: -0.0000

Data Index: 386659 (The Pile)

Max Activating Token Index: 737

Text #19

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1188. Min Act: -0.0000

Data Index: 1849907 (The Pile)

Max Activating Token Index: 307