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

Dataset: The Pile

Neuron 3020 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: 1.4390. Min Range: -1.4390

Max Act: 1.4390. Min Act: -0.0000

Data Index: 848406 (The Pile)

Max Activating Token Index: 290

Text #1

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.1875. Min Act: -0.0000

Data Index: 1254085 (The Pile)

Max Activating Token Index: 675

Text #2

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.9300. Min Act: -0.0000

Data Index: 1502843 (The Pile)

Max Activating Token Index: 124

Text #3

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.0915. Min Act: -0.0000

Data Index: 742710 (The Pile)

Max Activating Token Index: 354

Text #4

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.0452. Min Act: -0.0000

Data Index: 770070 (The Pile)

Max Activating Token Index: 596

Text #5

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.1090. Min Act: -0.0000

Data Index: 824391 (The Pile)

Max Activating Token Index: 982

Text #6

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.9977. Min Act: -0.0000

Data Index: 847388 (The Pile)

Max Activating Token Index: 372

Text #7

Max Range: 1.4390. Min Range: -1.4390

Max Act: 1.0293. Min Act: -0.0000

Data Index: 1855079 (The Pile)

Max Activating Token Index: 961

Text #8

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1887172 (The Pile)

Max Activating Token Index: 85

Text #9

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.8068. Min Act: -0.0000

Data Index: 863809 (The Pile)

Max Activating Token Index: 836

Text #10

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.9694. Min Act: -0.0000

Data Index: 570542 (The Pile)

Max Activating Token Index: 883

Text #11

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.9554. Min Act: -0.0000

Data Index: 1675538 (The Pile)

Max Activating Token Index: 201

Text #12

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.8783. Min Act: -0.0000

Data Index: 1251389 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.9854. Min Act: -0.0000

Data Index: 1690097 (The Pile)

Max Activating Token Index: 745

Text #14

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.9241. Min Act: -0.0000

Data Index: 1492250 (The Pile)

Max Activating Token Index: 675

Text #15

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.8657. Min Act: -0.0000

Data Index: 1704296 (The Pile)

Max Activating Token Index: 908

Text #16

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.8108. Min Act: -0.0000

Data Index: 596288 (The Pile)

Max Activating Token Index: 875

Text #17

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.8998. Min Act: -0.0000

Data Index: 517028 (The Pile)

Max Activating Token Index: 376

Text #18

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.8641. Min Act: -0.0000

Data Index: 810843 (The Pile)

Max Activating Token Index: 794

Text #19

Max Range: 1.4390. Min Range: -1.4390

Max Act: 0.9241. Min Act: -0.0000

Data Index: 102814 (The Pile)

Max Activating Token Index: 623