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

Dataset: The Pile

Neuron 3953 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.9062. Min Act: -0.0000

Data Index: 356080 (The Pile)

Max Activating Token Index: 764

Text #1

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.8761. Min Act: -0.0000

Data Index: 369081 (The Pile)

Max Activating Token Index: 863

Text #2

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.8038. Min Act: -0.0000

Data Index: 1349853 (The Pile)

Max Activating Token Index: 410

Text #3

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.9261. Min Act: -0.0000

Data Index: 209208 (The Pile)

Max Activating Token Index: 181

Text #4

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7987. Min Act: -0.0000

Data Index: 819393 (The Pile)

Max Activating Token Index: 560

Text #5

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6878. Min Act: -0.0000

Data Index: 17221 (The Pile)

Max Activating Token Index: 233

Text #6

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6828. Min Act: -0.0000

Data Index: 830201 (The Pile)

Max Activating Token Index: 562

Text #7

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6579. Min Act: -0.0000

Data Index: 1228514 (The Pile)

Max Activating Token Index: 501

Text #8

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6114. Min Act: -0.0000

Data Index: 1623621 (The Pile)

Max Activating Token Index: 854

Text #9

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6736. Min Act: -0.0000

Data Index: 97311 (The Pile)

Max Activating Token Index: 440

Text #10

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6143. Min Act: -0.0000

Data Index: 758154 (The Pile)

Max Activating Token Index: 508

Text #11

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6410. Min Act: -0.0000

Data Index: 953032 (The Pile)

Max Activating Token Index: 877

Text #12

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6567. Min Act: -0.0000

Data Index: 1379546 (The Pile)

Max Activating Token Index: 534

Text #13

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7047. Min Act: -0.0000

Data Index: 27052 (The Pile)

Max Activating Token Index: 671

Text #14

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6196. Min Act: -0.0000

Data Index: 744302 (The Pile)

Max Activating Token Index: 697

Text #15

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1503802 (The Pile)

Max Activating Token Index: 828

Text #16

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.6090. Min Act: -0.0000

Data Index: 1038625 (The Pile)

Max Activating Token Index: 741

Text #17

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.5729. Min Act: -0.0000

Data Index: 117587 (The Pile)

Max Activating Token Index: 1000

Text #18

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.5236. Min Act: -0.0000

Data Index: 1831155 (The Pile)

Max Activating Token Index: 922

Text #19

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.5654. Min Act: -0.0000

Data Index: 1437293 (The Pile)

Max Activating Token Index: 42