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

Dataset: The Pile

Neuron 1957 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: 0.5834. Min Range: -0.5834

Max Act: 0.5834. Min Act: -0.0000

Data Index: 1485427 (The Pile)

Max Activating Token Index: 295

Text #1

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4663. Min Act: -0.0000

Data Index: 1101950 (The Pile)

Max Activating Token Index: 533

Text #2

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4697. Min Act: -0.0000

Data Index: 465600 (The Pile)

Max Activating Token Index: 506

Text #3

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.5023. Min Act: -0.0000

Data Index: 992788 (The Pile)

Max Activating Token Index: 485

Text #4

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4968. Min Act: -0.0000

Data Index: 1454749 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4858. Min Act: -0.0000

Data Index: 538574 (The Pile)

Max Activating Token Index: 530

Text #6

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4627. Min Act: -0.0000

Data Index: 816299 (The Pile)

Max Activating Token Index: 766

Text #7

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4733. Min Act: -0.0000

Data Index: 228682 (The Pile)

Max Activating Token Index: 795

Text #8

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4558. Min Act: -0.0000

Data Index: 522017 (The Pile)

Max Activating Token Index: 412

Text #9

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1462947 (The Pile)

Max Activating Token Index: 947

Text #10

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4740. Min Act: -0.0000

Data Index: 284465 (The Pile)

Max Activating Token Index: 787

Text #11

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1034806 (The Pile)

Max Activating Token Index: 342

Text #12

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4705. Min Act: -0.0000

Data Index: 1043274 (The Pile)

Max Activating Token Index: 870

Text #13

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4924. Min Act: -0.0001

Data Index: 70160 (The Pile)

Max Activating Token Index: 701

Text #14

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4400. Min Act: -0.0000

Data Index: 1088157 (The Pile)

Max Activating Token Index: 217

Text #15

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4625. Min Act: -0.0000

Data Index: 424774 (The Pile)

Max Activating Token Index: 113

Text #16

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4391. Min Act: -0.0000

Data Index: 1083642 (The Pile)

Max Activating Token Index: 459

Text #17

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4758. Min Act: -0.0000

Data Index: 745371 (The Pile)

Max Activating Token Index: 729

Text #18

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.4454. Min Act: -0.0000

Data Index: 1678201 (The Pile)

Max Activating Token Index: 866

Text #19

Max Range: 0.5834. Min Range: -0.5834

Max Act: 0.3977. Min Act: -0.0000

Data Index: 1325084 (The Pile)

Max Activating Token Index: 244