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

Dataset: The Pile

Neuron 3014 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.9150. Min Act: -0.0000

Data Index: 354754 (The Pile)

Max Activating Token Index: 54

Text #1

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.6806. Min Act: -0.0000

Data Index: 1147862 (The Pile)

Max Activating Token Index: 799

Text #2

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.6944. Min Act: -0.0000

Data Index: 521856 (The Pile)

Max Activating Token Index: 643

Text #3

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.5564. Min Act: -0.0000

Data Index: 636462 (The Pile)

Max Activating Token Index: 333

Text #4

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.6492. Min Act: -0.0000

Data Index: 1761255 (The Pile)

Max Activating Token Index: 514

Text #5

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.5416. Min Act: -0.0000

Data Index: 1451449 (The Pile)

Max Activating Token Index: 882

Text #6

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.5339. Min Act: -0.0000

Data Index: 481414 (The Pile)

Max Activating Token Index: 604

Text #7

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.5393. Min Act: -0.0000

Data Index: 786315 (The Pile)

Max Activating Token Index: 669

Text #8

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.5286. Min Act: -0.0000

Data Index: 734413 (The Pile)

Max Activating Token Index: 734

Text #9

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.6440. Min Act: -0.0000

Data Index: 1195159 (The Pile)

Max Activating Token Index: 909

Text #10

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.5883. Min Act: -0.0000

Data Index: 147214 (The Pile)

Max Activating Token Index: 508

Text #11

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.5900. Min Act: -0.0000

Data Index: 1971801 (The Pile)

Max Activating Token Index: 540

Text #12

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.5668. Min Act: -0.0000

Data Index: 1394827 (The Pile)

Max Activating Token Index: 401

Text #13

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.4701. Min Act: -0.0000

Data Index: 400674 (The Pile)

Max Activating Token Index: 678

Text #14

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.4859. Min Act: -0.0000

Data Index: 685840 (The Pile)

Max Activating Token Index: 252

Text #15

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.5639. Min Act: -0.0000

Data Index: 838435 (The Pile)

Max Activating Token Index: 513

Text #16

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.6468. Min Act: -0.0000

Data Index: 1580167 (The Pile)

Max Activating Token Index: 531

Text #17

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.4753. Min Act: -0.0000

Data Index: 1870258 (The Pile)

Max Activating Token Index: 886

Text #18

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.5661. Min Act: -0.0000

Data Index: 1629887 (The Pile)

Max Activating Token Index: 345

Text #19

Max Range: 1.9150. Min Range: -1.9150

Max Act: 1.5616. Min Act: -0.0000

Data Index: 548968 (The Pile)

Max Activating Token Index: 366