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

Dataset: The Pile

Neuron 515 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: 3.0551. Min Range: -3.0551

Max Act: 3.0551. Min Act: -0.0000

Data Index: 485412 (The Pile)

Max Activating Token Index: 238

Text #1

Max Range: 3.0551. Min Range: -3.0551

Max Act: 2.7470. Min Act: -0.0000

Data Index: 56337 (The Pile)

Max Activating Token Index: 1011

Text #2

Max Range: 3.0551. Min Range: -3.0551

Max Act: 2.5342. Min Act: -0.0000

Data Index: 1565492 (The Pile)

Max Activating Token Index: 374

Text #3

Max Range: 3.0551. Min Range: -3.0551

Max Act: 2.6210. Min Act: -0.0000

Data Index: 405821 (The Pile)

Max Activating Token Index: 992

Text #4

Max Range: 3.0551. Min Range: -3.0551

Max Act: 2.5996. Min Act: -0.0000

Data Index: 283088 (The Pile)

Max Activating Token Index: 266

Text #5

Max Range: 3.0551. Min Range: -3.0551

Max Act: 2.5820. Min Act: -0.0000

Data Index: 1501610 (The Pile)

Max Activating Token Index: 147

Text #6

Max Range: 3.0551. Min Range: -3.0551

Max Act: 2.4359. Min Act: -0.0000

Data Index: 1558214 (The Pile)

Max Activating Token Index: 341

Text #7

Max Range: 3.0551. Min Range: -3.0551

Max Act: 2.5389. Min Act: -0.0000

Data Index: 1976672 (The Pile)

Max Activating Token Index: 928

Text #8

Max Range: 3.0551. Min Range: -3.0551

Max Act: 2.4924. Min Act: -0.0000

Data Index: 1307820 (The Pile)

Max Activating Token Index: 466

Text #9

Max Range: 3.0551. Min Range: -3.0551

Max Act: 2.4683. Min Act: -0.0000

Data Index: 331765 (The Pile)

Max Activating Token Index: 278

Text #10

Max Range: 3.0551. Min Range: -3.0551

Max Act: 2.3460. Min Act: -0.0000

Data Index: 1917190 (The Pile)

Max Activating Token Index: 190

Text #11

Max Range: 3.0551. Min Range: -3.0551

Max Act: 2.3839. Min Act: -0.0000

Data Index: 1287197 (The Pile)

Max Activating Token Index: 775

Text #12

Max Range: 3.0551. Min Range: -3.0551

Max Act: 2.4610. Min Act: -0.0000

Data Index: 240231 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 3.0551. Min Range: -3.0551

Max Act: 2.4658. Min Act: -0.0000

Data Index: 1032107 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 3.0551. Min Range: -3.0551

Max Act: 2.3320. Min Act: -0.0000

Data Index: 1134122 (The Pile)

Max Activating Token Index: 426

Text #15

Max Range: 3.0551. Min Range: -3.0551

Max Act: 2.4439. Min Act: -0.0000

Data Index: 1828431 (The Pile)

Max Activating Token Index: 818

Text #16

Max Range: 3.0551. Min Range: -3.0551

Max Act: 2.4379. Min Act: -0.0000

Data Index: 1328457 (The Pile)

Max Activating Token Index: 808

Text #17

Max Range: 3.0551. Min Range: -3.0551

Max Act: 2.3155. Min Act: -0.0000

Data Index: 1052608 (The Pile)

Max Activating Token Index: 390

Text #18

Max Range: 3.0551. Min Range: -3.0551

Max Act: 2.4247. Min Act: -0.0000

Data Index: 1504365 (The Pile)

Max Activating Token Index: 386

Text #19

Max Range: 3.0551. Min Range: -3.0551

Max Act: 2.1674. Min Act: -0.0000

Data Index: 1185001 (The Pile)

Max Activating Token Index: 177