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

Dataset: The Pile

Neuron 1837 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: 0.6427. Min Range: -0.6427

Max Act: 0.6427. Min Act: -0.0000

Data Index: 1126957 (The Pile)

Max Activating Token Index: 335

Text #1

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1189177 (The Pile)

Max Activating Token Index: 233

Text #2

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.5531. Min Act: -0.0000

Data Index: 1932236 (The Pile)

Max Activating Token Index: 359

Text #3

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.5624. Min Act: -0.0000

Data Index: 1711433 (The Pile)

Max Activating Token Index: 269

Text #4

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4852. Min Act: -0.0000

Data Index: 1623077 (The Pile)

Max Activating Token Index: 473

Text #5

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.5316. Min Act: -0.0000

Data Index: 487015 (The Pile)

Max Activating Token Index: 866

Text #6

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1733567 (The Pile)

Max Activating Token Index: 261

Text #7

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1958826 (The Pile)

Max Activating Token Index: 596

Text #8

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4767. Min Act: -0.0000

Data Index: 1638252 (The Pile)

Max Activating Token Index: 90

Text #9

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4861. Min Act: -0.0000

Data Index: 1081752 (The Pile)

Max Activating Token Index: 690

Text #10

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4766. Min Act: -0.0000

Data Index: 463207 (The Pile)

Max Activating Token Index: 738

Text #11

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4612. Min Act: -0.0000

Data Index: 1679205 (The Pile)

Max Activating Token Index: 794

Text #12

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4759. Min Act: -0.0000

Data Index: 1718524 (The Pile)

Max Activating Token Index: 171

Text #13

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4708. Min Act: -0.0000

Data Index: 578600 (The Pile)

Max Activating Token Index: 867

Text #14

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4474. Min Act: -0.0000

Data Index: 613869 (The Pile)

Max Activating Token Index: 275

Text #15

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4455. Min Act: -0.0000

Data Index: 912526 (The Pile)

Max Activating Token Index: 300

Text #16

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4452. Min Act: -0.0000

Data Index: 960588 (The Pile)

Max Activating Token Index: 603

Text #17

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4455. Min Act: -0.0000

Data Index: 901446 (The Pile)

Max Activating Token Index: 565

Text #18

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4427. Min Act: -0.0000

Data Index: 293357 (The Pile)

Max Activating Token Index: 26

Text #19

Max Range: 0.6427. Min Range: -0.6427

Max Act: 0.4125. Min Act: -0.0000

Data Index: 1616525 (The Pile)

Max Activating Token Index: 1022