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

Dataset: The Pile

Neuron 1416 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: 3.1460. Min Range: -3.1460

Max Act: 2.9200. Min Act: -0.0000

Data Index: 1563785 (The Pile)

Max Activating Token Index: 504

Text #1

Max Range: 3.1460. Min Range: -3.1460

Max Act: 2.4794. Min Act: -0.0000

Data Index: 1034123 (The Pile)

Max Activating Token Index: 747

Text #2

Max Range: 3.1460. Min Range: -3.1460

Max Act: 2.3609. Min Act: -0.0000

Data Index: 623057 (The Pile)

Max Activating Token Index: 261

Text #3

Max Range: 3.1460. Min Range: -3.1460

Max Act: 3.1460. Min Act: -0.0000

Data Index: 1755605 (The Pile)

Max Activating Token Index: 338

Text #4

Max Range: 3.1460. Min Range: -3.1460

Max Act: 2.3685. Min Act: -0.0000

Data Index: 867862 (The Pile)

Max Activating Token Index: 802

Text #5

Max Range: 3.1460. Min Range: -3.1460

Max Act: 3.0746. Min Act: -0.0000

Data Index: 1215297 (The Pile)

Max Activating Token Index: 732

Text #6

Max Range: 3.1460. Min Range: -3.1460

Max Act: 2.6954. Min Act: -0.0000

Data Index: 1153216 (The Pile)

Max Activating Token Index: 354

Text #7

Max Range: 3.1460. Min Range: -3.1460

Max Act: 2.5770. Min Act: -0.0000

Data Index: 1981182 (The Pile)

Max Activating Token Index: 945

Text #8

Max Range: 3.1460. Min Range: -3.1460

Max Act: 2.8037. Min Act: -0.0000

Data Index: 1725520 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 3.1460. Min Range: -3.1460

Max Act: 2.5859. Min Act: -0.0000

Data Index: 1960162 (The Pile)

Max Activating Token Index: 243

Text #10

Max Range: 3.1460. Min Range: -3.1460

Max Act: 2.0655. Min Act: -0.0000

Data Index: 1930279 (The Pile)

Max Activating Token Index: 885

Text #11

Max Range: 3.1460. Min Range: -3.1460

Max Act: 2.3988. Min Act: -0.0000

Data Index: 601325 (The Pile)

Max Activating Token Index: 906

Text #12

Max Range: 3.1460. Min Range: -3.1460

Max Act: 2.5149. Min Act: -0.0000

Data Index: 884665 (The Pile)

Max Activating Token Index: 533

Text #13

Max Range: 3.1460. Min Range: -3.1460

Max Act: 2.1385. Min Act: -0.0000

Data Index: 1236811 (The Pile)

Max Activating Token Index: 381

Text #14

Max Range: 3.1460. Min Range: -3.1460

Max Act: 2.5549. Min Act: -0.0000

Data Index: 1478926 (The Pile)

Max Activating Token Index: 341

Text #15

Max Range: 3.1460. Min Range: -3.1460

Max Act: 2.0954. Min Act: -0.0000

Data Index: 1819561 (The Pile)

Max Activating Token Index: 678

Text #16

Max Range: 3.1460. Min Range: -3.1460

Max Act: 2.2854. Min Act: -0.0000

Data Index: 893334 (The Pile)

Max Activating Token Index: 284

Text #17

Max Range: 3.1460. Min Range: -3.1460

Max Act: 1.7584. Min Act: -0.0000

Data Index: 1590234 (The Pile)

Max Activating Token Index: 515

Text #18

Max Range: 3.1460. Min Range: -3.1460

Max Act: 2.2321. Min Act: -0.0000

Data Index: 621123 (The Pile)

Max Activating Token Index: 326

Text #19

Max Range: 3.1460. Min Range: -3.1460

Max Act: 2.0400. Min Act: -0.0000

Data Index: 577768 (The Pile)

Max Activating Token Index: 962