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

Dataset: The Pile

Neuron 1762 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.9237. Min Act: -0.0000

Data Index: 536910 (The Pile)

Max Activating Token Index: 718

Text #1

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.5500. Min Act: -0.0000

Data Index: 16349 (The Pile)

Max Activating Token Index: 260

Text #2

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.4794. Min Act: -0.0000

Data Index: 145161 (The Pile)

Max Activating Token Index: 375

Text #3

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.2303. Min Act: -0.0000

Data Index: 1752040 (The Pile)

Max Activating Token Index: 768

Text #4

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.3673. Min Act: -0.0000

Data Index: 1730740 (The Pile)

Max Activating Token Index: 280

Text #5

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.3671. Min Act: -0.0000

Data Index: 1115509 (The Pile)

Max Activating Token Index: 603

Text #6

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.6348. Min Act: -0.0000

Data Index: 884479 (The Pile)

Max Activating Token Index: 863

Text #7

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.4812. Min Act: -0.0000

Data Index: 420965 (The Pile)

Max Activating Token Index: 343

Text #8

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.1825. Min Act: -0.0000

Data Index: 671950 (The Pile)

Max Activating Token Index: 719

Text #9

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.1917. Min Act: -0.0000

Data Index: 574024 (The Pile)

Max Activating Token Index: 584

Text #10

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.1555. Min Act: -0.0000

Data Index: 1900269 (The Pile)

Max Activating Token Index: 759

Text #11

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.1201. Min Act: -0.0000

Data Index: 91363 (The Pile)

Max Activating Token Index: 725

Text #12

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.1495. Min Act: -0.0000

Data Index: 1183360 (The Pile)

Max Activating Token Index: 524

Text #13

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.2667. Min Act: -0.0000

Data Index: 2226 (The Pile)

Max Activating Token Index: 892

Text #14

Max Range: 3.9237. Min Range: -3.9237

Max Act: 2.9398. Min Act: -0.0000

Data Index: 582704 (The Pile)

Max Activating Token Index: 593

Text #15

Max Range: 3.9237. Min Range: -3.9237

Max Act: 2.9114. Min Act: -0.0000

Data Index: 1669742 (The Pile)

Max Activating Token Index: 650

Text #16

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.1223. Min Act: -0.0000

Data Index: 968017 (The Pile)

Max Activating Token Index: 970

Text #17

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.2011. Min Act: -0.0000

Data Index: 619897 (The Pile)

Max Activating Token Index: 383

Text #18

Max Range: 3.9237. Min Range: -3.9237

Max Act: 3.1594. Min Act: -0.0000

Data Index: 1473516 (The Pile)

Max Activating Token Index: 937

Text #19

Max Range: 3.9237. Min Range: -3.9237

Max Act: 2.9854. Min Act: -0.0000

Data Index: 1098461 (The Pile)

Max Activating Token Index: 515