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

Dataset: The Pile

Neuron 4752 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.6357. Min Act: -0.0000

Data Index: 490770 (The Pile)

Max Activating Token Index: 693

Text #1

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.6629. Min Act: -0.0000

Data Index: 29582 (The Pile)

Max Activating Token Index: 166

Text #2

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.6179. Min Act: -0.0000

Data Index: 1545533 (The Pile)

Max Activating Token Index: 502

Text #3

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5856. Min Act: -0.0000

Data Index: 736366 (The Pile)

Max Activating Token Index: 949

Text #4

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5871. Min Act: -0.0000

Data Index: 1663888 (The Pile)

Max Activating Token Index: 417

Text #5

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5585. Min Act: -0.0000

Data Index: 1863368 (The Pile)

Max Activating Token Index: 369

Text #6

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4892. Min Act: -0.0000

Data Index: 861097 (The Pile)

Max Activating Token Index: 571

Text #7

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5009. Min Act: -0.0000

Data Index: 505713 (The Pile)

Max Activating Token Index: 458

Text #8

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5170. Min Act: -0.0000

Data Index: 1754479 (The Pile)

Max Activating Token Index: 139

Text #9

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4775. Min Act: -0.0000

Data Index: 345821 (The Pile)

Max Activating Token Index: 886

Text #10

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5165. Min Act: -0.0000

Data Index: 1659633 (The Pile)

Max Activating Token Index: 512

Text #11

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5114. Min Act: -0.0000

Data Index: 1782208 (The Pile)

Max Activating Token Index: 376

Text #12

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5093. Min Act: -0.0000

Data Index: 1066252 (The Pile)

Max Activating Token Index: 698

Text #13

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4879. Min Act: -0.0000

Data Index: 1673247 (The Pile)

Max Activating Token Index: 160

Text #14

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4796. Min Act: -0.0000

Data Index: 20545 (The Pile)

Max Activating Token Index: 709

Text #15

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5024. Min Act: -0.0000

Data Index: 244476 (The Pile)

Max Activating Token Index: 343

Text #16

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1483359 (The Pile)

Max Activating Token Index: 266

Text #17

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4711. Min Act: -0.0000

Data Index: 936083 (The Pile)

Max Activating Token Index: 193

Text #18

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1338373 (The Pile)

Max Activating Token Index: 923

Text #19

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.4894. Min Act: -0.0000

Data Index: 1663732 (The Pile)

Max Activating Token Index: 948