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

Dataset: The Pile

Neuron 1801 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.6661. Min Act: -0.0000

Data Index: 328767 (The Pile)

Max Activating Token Index: 557

Text #1

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.6908. Min Act: -0.0000

Data Index: 1445324 (The Pile)

Max Activating Token Index: 346

Text #2

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.6440. Min Act: -0.0000

Data Index: 73957 (The Pile)

Max Activating Token Index: 251

Text #3

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.6604. Min Act: -0.0000

Data Index: 1822097 (The Pile)

Max Activating Token Index: 577

Text #4

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.6251. Min Act: -0.0000

Data Index: 1172612 (The Pile)

Max Activating Token Index: 624

Text #5

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1518620 (The Pile)

Max Activating Token Index: 569

Text #6

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5841. Min Act: -0.0000

Data Index: 393565 (The Pile)

Max Activating Token Index: 838

Text #7

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5685. Min Act: -0.0000

Data Index: 1064878 (The Pile)

Max Activating Token Index: 748

Text #8

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5707. Min Act: -0.0000

Data Index: 1878940 (The Pile)

Max Activating Token Index: 717

Text #9

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5755. Min Act: -0.0000

Data Index: 262547 (The Pile)

Max Activating Token Index: 87

Text #10

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5492. Min Act: -0.0000

Data Index: 980893 (The Pile)

Max Activating Token Index: 536

Text #11

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1077416 (The Pile)

Max Activating Token Index: 582

Text #12

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5951. Min Act: -0.0000

Data Index: 1303021 (The Pile)

Max Activating Token Index: 394

Text #13

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1291414 (The Pile)

Max Activating Token Index: 189

Text #14

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.6133. Min Act: -0.0000

Data Index: 322017 (The Pile)

Max Activating Token Index: 228

Text #15

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5518. Min Act: -0.0000

Data Index: 1937348 (The Pile)

Max Activating Token Index: 564

Text #16

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5295. Min Act: -0.0000

Data Index: 470308 (The Pile)

Max Activating Token Index: 110

Text #17

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5241. Min Act: -0.0000

Data Index: 610464 (The Pile)

Max Activating Token Index: 405

Text #18

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5416. Min Act: 0.0000

Data Index: 504765 (The Pile)

Max Activating Token Index: 443

Text #19

Max Range: 0.6908. Min Range: -0.6908

Max Act: 0.5434. Min Act: -0.0000

Data Index: 601303 (The Pile)

Max Activating Token Index: 474