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

Dataset: The Pile

Neuron 3091 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: 0.1462. Min Range: -0.1462

Max Act: 0.1462. Min Act: -0.0000

Data Index: 730194 (The Pile)

Max Activating Token Index: 482

Text #1

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1438. Min Act: -0.0000

Data Index: 1813650 (The Pile)

Max Activating Token Index: 216

Text #2

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1348. Min Act: -0.0000

Data Index: 1385416 (The Pile)

Max Activating Token Index: 473

Text #3

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1283. Min Act: -0.0000

Data Index: 1845029 (The Pile)

Max Activating Token Index: 665

Text #4

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1228. Min Act: -0.0000

Data Index: 575592 (The Pile)

Max Activating Token Index: 533

Text #5

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1297. Min Act: -0.0000

Data Index: 1878863 (The Pile)

Max Activating Token Index: 698

Text #6

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1434. Min Act: -0.0000

Data Index: 1365689 (The Pile)

Max Activating Token Index: 992

Text #7

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1210. Min Act: -0.0000

Data Index: 664455 (The Pile)

Max Activating Token Index: 331

Text #8

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1159. Min Act: -0.0000

Data Index: 1263204 (The Pile)

Max Activating Token Index: 670

Text #9

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1059. Min Act: -0.0000

Data Index: 1326296 (The Pile)

Max Activating Token Index: 320

Text #10

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1061. Min Act: -0.0000

Data Index: 387480 (The Pile)

Max Activating Token Index: 294

Text #11

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0998. Min Act: -0.0000

Data Index: 834259 (The Pile)

Max Activating Token Index: 350

Text #12

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0861. Min Act: -0.0000

Data Index: 435038 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1760092 (The Pile)

Max Activating Token Index: 549

Text #14

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1560323 (The Pile)

Max Activating Token Index: 312

Text #15

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1001. Min Act: -0.0000

Data Index: 1687053 (The Pile)

Max Activating Token Index: 226

Text #16

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0962. Min Act: -0.0000

Data Index: 1997611 (The Pile)

Max Activating Token Index: 306

Text #17

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.1020. Min Act: -0.0000

Data Index: 413212 (The Pile)

Max Activating Token Index: 207

Text #18

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0951. Min Act: -0.0000

Data Index: 1304615 (The Pile)

Max Activating Token Index: 835

Text #19

Max Range: 0.1462. Min Range: -0.1462

Max Act: 0.0874. Min Act: -0.0000

Data Index: 182433 (The Pile)

Max Activating Token Index: 755