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

Dataset: The Pile

Neuron 4323 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.9488. Min Act: -0.0000

Data Index: 1243739 (The Pile)

Max Activating Token Index: 941

Text #1

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.8474. Min Act: -0.0000

Data Index: 1467583 (The Pile)

Max Activating Token Index: 370

Text #2

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.7384. Min Act: -0.0000

Data Index: 832180 (The Pile)

Max Activating Token Index: 824

Text #3

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.2249. Min Act: -0.0000

Data Index: 1721780 (The Pile)

Max Activating Token Index: 790

Text #4

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.4150. Min Act: -0.0000

Data Index: 329419 (The Pile)

Max Activating Token Index: 412

Text #5

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.4213. Min Act: -0.0000

Data Index: 1985668 (The Pile)

Max Activating Token Index: 793

Text #6

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.0485. Min Act: -0.0000

Data Index: 959564 (The Pile)

Max Activating Token Index: 965

Text #7

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.3461. Min Act: -0.0000

Data Index: 1873475 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.0279. Min Act: -0.0000

Data Index: 336251 (The Pile)

Max Activating Token Index: 490

Text #9

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.3307. Min Act: -0.0000

Data Index: 1776194 (The Pile)

Max Activating Token Index: 1005

Text #10

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.3944. Min Act: -0.0000

Data Index: 1529868 (The Pile)

Max Activating Token Index: 964

Text #11

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.3494. Min Act: -0.0000

Data Index: 1660160 (The Pile)

Max Activating Token Index: 876

Text #12

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.2426. Min Act: -0.0000

Data Index: 509335 (The Pile)

Max Activating Token Index: 661

Text #13

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.3604. Min Act: -0.0000

Data Index: 1811802 (The Pile)

Max Activating Token Index: 273

Text #14

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.1922. Min Act: -0.0000

Data Index: 923205 (The Pile)

Max Activating Token Index: 94

Text #15

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.1435. Min Act: -0.0000

Data Index: 1790557 (The Pile)

Max Activating Token Index: 897

Text #16

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.3924. Min Act: -0.0000

Data Index: 1067012 (The Pile)

Max Activating Token Index: 901

Text #17

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.2414. Min Act: -0.0000

Data Index: 110636 (The Pile)

Max Activating Token Index: 863

Text #18

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.0770. Min Act: -0.0000

Data Index: 1073189 (The Pile)

Max Activating Token Index: 722

Text #19

Max Range: 1.9488. Min Range: -1.9488

Max Act: 1.2880. Min Act: -0.0000

Data Index: 349867 (The Pile)

Max Activating Token Index: 224