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

Dataset: The Pile

Neuron 1423 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6339. Min Range: -1.6339

Max Act: 1.6339. Min Act: -0.0000

Data Index: 669396 (The Pile)

Max Activating Token Index: 265

Text #1

Max Range: 1.6339. Min Range: -1.6339

Max Act: 1.5558. Min Act: -0.0000

Data Index: 1293705 (The Pile)

Max Activating Token Index: 530

Text #2

Max Range: 1.6339. Min Range: -1.6339

Max Act: 1.3559. Min Act: -0.0000

Data Index: 1525230 (The Pile)

Max Activating Token Index: 985

Text #3

Max Range: 1.6339. Min Range: -1.6339

Max Act: 1.2522. Min Act: -0.0000

Data Index: 155752 (The Pile)

Max Activating Token Index: 150

Text #4

Max Range: 1.6339. Min Range: -1.6339

Max Act: 1.2084. Min Act: -0.0000

Data Index: 135741 (The Pile)

Max Activating Token Index: 834

Text #5

Max Range: 1.6339. Min Range: -1.6339

Max Act: 1.1017. Min Act: -0.0000

Data Index: 645126 (The Pile)

Max Activating Token Index: 368

Text #6

Max Range: 1.6339. Min Range: -1.6339

Max Act: 0.9430. Min Act: -0.0000

Data Index: 1250448 (The Pile)

Max Activating Token Index: 830

Text #7

Max Range: 1.6339. Min Range: -1.6339

Max Act: 1.0772. Min Act: -0.0000

Data Index: 1781963 (The Pile)

Max Activating Token Index: 84

Text #8

Max Range: 1.6339. Min Range: -1.6339

Max Act: 1.0791. Min Act: -0.0000

Data Index: 1102711 (The Pile)

Max Activating Token Index: 704

Text #9

Max Range: 1.6339. Min Range: -1.6339

Max Act: 1.0419. Min Act: -0.0000

Data Index: 934808 (The Pile)

Max Activating Token Index: 235

Text #10

Max Range: 1.6339. Min Range: -1.6339

Max Act: 1.0910. Min Act: -0.0000

Data Index: 1582847 (The Pile)

Max Activating Token Index: 509

Text #11

Max Range: 1.6339. Min Range: -1.6339

Max Act: 1.0661. Min Act: -0.0000

Data Index: 345949 (The Pile)

Max Activating Token Index: 497

Text #12

Max Range: 1.6339. Min Range: -1.6339

Max Act: 0.9286. Min Act: -0.0000

Data Index: 1190271 (The Pile)

Max Activating Token Index: 622

Text #13

Max Range: 1.6339. Min Range: -1.6339

Max Act: 1.0677. Min Act: -0.0000

Data Index: 627851 (The Pile)

Max Activating Token Index: 331

Text #14

Max Range: 1.6339. Min Range: -1.6339

Max Act: 0.9367. Min Act: -0.0000

Data Index: 1203404 (The Pile)

Max Activating Token Index: 513

Text #15

Max Range: 1.6339. Min Range: -1.6339

Max Act: 0.9943. Min Act: -0.0000

Data Index: 1192899 (The Pile)

Max Activating Token Index: 812

Text #16

Max Range: 1.6339. Min Range: -1.6339

Max Act: 0.9843. Min Act: -0.0000

Data Index: 521674 (The Pile)

Max Activating Token Index: 513

Text #17

Max Range: 1.6339. Min Range: -1.6339

Max Act: 0.9843. Min Act: -0.0000

Data Index: 612297 (The Pile)

Max Activating Token Index: 748

Text #18

Max Range: 1.6339. Min Range: -1.6339

Max Act: 1.1412. Min Act: -0.0000

Data Index: 1320227 (The Pile)

Max Activating Token Index: 715

Text #19

Max Range: 1.6339. Min Range: -1.6339

Max Act: 0.9757. Min Act: -0.0000

Data Index: 1178403 (The Pile)

Max Activating Token Index: 1002