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

Dataset: The Pile

Neuron 595 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: 1.5671. Min Range: -1.5671

Max Act: 1.5671. Min Act: -0.0000

Data Index: 415226 (The Pile)

Max Activating Token Index: 18

Text #1

Max Range: 1.5671. Min Range: -1.5671

Max Act: 1.1785. Min Act: -0.0000

Data Index: 679338 (The Pile)

Max Activating Token Index: 9

Text #2

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.8159. Min Act: -0.0000

Data Index: 674348 (The Pile)

Max Activating Token Index: 10

Text #3

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.7702. Min Act: -0.0000

Data Index: 1990600 (The Pile)

Max Activating Token Index: 7

Text #4

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.8261. Min Act: -0.0000

Data Index: 526269 (The Pile)

Max Activating Token Index: 11

Text #5

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.7875. Min Act: -0.0000

Data Index: 530121 (The Pile)

Max Activating Token Index: 14

Text #6

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1806928 (The Pile)

Max Activating Token Index: 13

Text #7

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.7386. Min Act: -0.0000

Data Index: 531934 (The Pile)

Max Activating Token Index: 5

Text #8

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.7064. Min Act: -0.0000

Data Index: 944282 (The Pile)

Max Activating Token Index: 9

Text #9

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.5871. Min Act: -0.0000

Data Index: 1691449 (The Pile)

Max Activating Token Index: 399

Text #10

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.6581. Min Act: -0.0000

Data Index: 1171726 (The Pile)

Max Activating Token Index: 13

Text #11

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.6515. Min Act: -0.0000

Data Index: 1735081 (The Pile)

Max Activating Token Index: 20

Text #12

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.5722. Min Act: -0.0000

Data Index: 143124 (The Pile)

Max Activating Token Index: 7

Text #13

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1570354 (The Pile)

Max Activating Token Index: 436

Text #14

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.6258. Min Act: -0.0000

Data Index: 1287719 (The Pile)

Max Activating Token Index: 10

Text #15

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.5651. Min Act: -0.0000

Data Index: 657721 (The Pile)

Max Activating Token Index: 15

Text #16

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.5253. Min Act: -0.0000

Data Index: 1851193 (The Pile)

Max Activating Token Index: 18

Text #17

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.4827. Min Act: -0.0000

Data Index: 1542841 (The Pile)

Max Activating Token Index: 4

Text #18

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1856667 (The Pile)

Max Activating Token Index: 230

Text #19

Max Range: 1.5671. Min Range: -1.5671

Max Act: 0.5753. Min Act: -0.0000

Data Index: 507169 (The Pile)

Max Activating Token Index: 8