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

Dataset: The Pile

Neuron 3760 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: 0.8240. Min Range: -0.8240

Max Act: 0.7868. Min Act: -0.0000

Data Index: 918483 (The Pile)

Max Activating Token Index: 8

Text #1

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.8240. Min Act: -0.0000

Data Index: 700450 (The Pile)

Max Activating Token Index: 561

Text #2

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.8194. Min Act: -0.0000

Data Index: 1088551 (The Pile)

Max Activating Token Index: 497

Text #3

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7702. Min Act: -0.0000

Data Index: 680847 (The Pile)

Max Activating Token Index: 824

Text #4

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7689. Min Act: -0.0000

Data Index: 1254860 (The Pile)

Max Activating Token Index: 330

Text #5

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7655. Min Act: -0.0000

Data Index: 1902363 (The Pile)

Max Activating Token Index: 922

Text #6

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7074. Min Act: -0.0000

Data Index: 875706 (The Pile)

Max Activating Token Index: 764

Text #7

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7017. Min Act: -0.0000

Data Index: 621820 (The Pile)

Max Activating Token Index: 350

Text #8

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6834. Min Act: -0.0000

Data Index: 1161814 (The Pile)

Max Activating Token Index: 377

Text #9

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6824. Min Act: -0.0000

Data Index: 1562569 (The Pile)

Max Activating Token Index: 253

Text #10

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1497856 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6331. Min Act: -0.0000

Data Index: 1534136 (The Pile)

Max Activating Token Index: 865

Text #12

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7123. Min Act: -0.0000

Data Index: 1163553 (The Pile)

Max Activating Token Index: 927

Text #13

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6653. Min Act: -0.0000

Data Index: 1005798 (The Pile)

Max Activating Token Index: 945

Text #14

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6558. Min Act: -0.0000

Data Index: 204225 (The Pile)

Max Activating Token Index: 201

Text #15

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1774433 (The Pile)

Max Activating Token Index: 312

Text #16

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6537. Min Act: -0.0000

Data Index: 1817684 (The Pile)

Max Activating Token Index: 459

Text #17

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1352039 (The Pile)

Max Activating Token Index: 346

Text #18

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1975491 (The Pile)

Max Activating Token Index: 25

Text #19

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.6877. Min Act: -0.0000

Data Index: 1444926 (The Pile)

Max Activating Token Index: 890