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

Dataset: The Pile

Neuron 3547 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: 1.7087. Min Range: -1.7087

Max Act: 1.7087. Min Act: -0.0000

Data Index: 385801 (The Pile)

Max Activating Token Index: 948

Text #1

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.6849. Min Act: -0.0000

Data Index: 1838457 (The Pile)

Max Activating Token Index: 774

Text #2

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.3948. Min Act: -0.0000

Data Index: 1066048 (The Pile)

Max Activating Token Index: 353

Text #3

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.2401. Min Act: -0.0000

Data Index: 95645 (The Pile)

Max Activating Token Index: 523

Text #4

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.3705. Min Act: -0.0000

Data Index: 2885 (The Pile)

Max Activating Token Index: 473

Text #5

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.2978. Min Act: -0.0000

Data Index: 1661944 (The Pile)

Max Activating Token Index: 465

Text #6

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.1576. Min Act: -0.0000

Data Index: 649596 (The Pile)

Max Activating Token Index: 973

Text #7

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.3457. Min Act: -0.0000

Data Index: 60277 (The Pile)

Max Activating Token Index: 983

Text #8

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.3248. Min Act: -0.0000

Data Index: 1680152 (The Pile)

Max Activating Token Index: 721

Text #9

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.0221. Min Act: -0.0000

Data Index: 779017 (The Pile)

Max Activating Token Index: 886

Text #10

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.3098. Min Act: -0.0000

Data Index: 1793732 (The Pile)

Max Activating Token Index: 867

Text #11

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.1100. Min Act: -0.0000

Data Index: 1384496 (The Pile)

Max Activating Token Index: 541

Text #12

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.0995. Min Act: -0.0000

Data Index: 1187230 (The Pile)

Max Activating Token Index: 485

Text #13

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1526499 (The Pile)

Max Activating Token Index: 386

Text #14

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.1391. Min Act: -0.0000

Data Index: 1205513 (The Pile)

Max Activating Token Index: 361

Text #15

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.1918. Min Act: -0.0000

Data Index: 1998491 (The Pile)

Max Activating Token Index: 710

Text #16

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.5568. Min Act: -0.0000

Data Index: 891272 (The Pile)

Max Activating Token Index: 922

Text #17

Max Range: 1.7087. Min Range: -1.7087

Max Act: 0.9687. Min Act: -0.0000

Data Index: 274952 (The Pile)

Max Activating Token Index: 721

Text #18

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.0460. Min Act: -0.0000

Data Index: 1674865 (The Pile)

Max Activating Token Index: 843

Text #19

Max Range: 1.7087. Min Range: -1.7087

Max Act: 1.1378. Min Act: -0.0000

Data Index: 1686086 (The Pile)

Max Activating Token Index: 307