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

Dataset: The Pile

Neuron 4289 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: 5.4029. Min Range: -5.4029

Max Act: 4.3917. Min Act: -0.0000

Data Index: 744302 (The Pile)

Max Activating Token Index: 728

Text #1

Max Range: 5.4029. Min Range: -5.4029

Max Act: 5.0446. Min Act: -0.0000

Data Index: 631872 (The Pile)

Max Activating Token Index: 390

Text #2

Max Range: 5.4029. Min Range: -5.4029

Max Act: 4.6086. Min Act: -0.0000

Data Index: 1622808 (The Pile)

Max Activating Token Index: 596

Text #3

Max Range: 5.4029. Min Range: -5.4029

Max Act: 4.9044. Min Act: -0.0000

Data Index: 97311 (The Pile)

Max Activating Token Index: 471

Text #4

Max Range: 5.4029. Min Range: -5.4029

Max Act: 5.1705. Min Act: -0.0000

Data Index: 1379546 (The Pile)

Max Activating Token Index: 565

Text #5

Max Range: 5.4029. Min Range: -5.4029

Max Act: 5.4029. Min Act: -0.0000

Data Index: 1228514 (The Pile)

Max Activating Token Index: 532

Text #6

Max Range: 5.4029. Min Range: -5.4029

Max Act: 4.1521. Min Act: -0.0000

Data Index: 830201 (The Pile)

Max Activating Token Index: 587

Text #7

Max Range: 5.4029. Min Range: -5.4029

Max Act: 4.5789. Min Act: -0.0000

Data Index: 27052 (The Pile)

Max Activating Token Index: 696

Text #8

Max Range: 5.4029. Min Range: -5.4029

Max Act: 4.3145. Min Act: -0.0000

Data Index: 209208 (The Pile)

Max Activating Token Index: 206

Text #9

Max Range: 5.4029. Min Range: -5.4029

Max Act: 4.2502. Min Act: -0.0000

Data Index: 1349853 (The Pile)

Max Activating Token Index: 435

Text #10

Max Range: 5.4029. Min Range: -5.4029

Max Act: 3.8143. Min Act: -0.0000

Data Index: 17221 (The Pile)

Max Activating Token Index: 258

Text #11

Max Range: 5.4029. Min Range: -5.4029

Max Act: 3.6028. Min Act: -0.0000

Data Index: 1038625 (The Pile)

Max Activating Token Index: 766

Text #12

Max Range: 5.4029. Min Range: -5.4029

Max Act: 3.7944. Min Act: -0.0000

Data Index: 1344595 (The Pile)

Max Activating Token Index: 275

Text #13

Max Range: 5.4029. Min Range: -5.4029

Max Act: 4.2536. Min Act: -0.0000

Data Index: 758154 (The Pile)

Max Activating Token Index: 527

Text #14

Max Range: 5.4029. Min Range: -5.4029

Max Act: 3.7875. Min Act: -0.0000

Data Index: 485677 (The Pile)

Max Activating Token Index: 331

Text #15

Max Range: 5.4029. Min Range: -5.4029

Max Act: 4.0529. Min Act: -0.0000

Data Index: 1008896 (The Pile)

Max Activating Token Index: 395

Text #16

Max Range: 5.4029. Min Range: -5.4029

Max Act: 3.8601. Min Act: -0.0000

Data Index: 463972 (The Pile)

Max Activating Token Index: 483

Text #17

Max Range: 5.4029. Min Range: -5.4029

Max Act: 4.1426. Min Act: -0.0000

Data Index: 100332 (The Pile)

Max Activating Token Index: 906

Text #18

Max Range: 5.4029. Min Range: -5.4029

Max Act: 3.7830. Min Act: -0.0000

Data Index: 1535108 (The Pile)

Max Activating Token Index: 612

Text #19

Max Range: 5.4029. Min Range: -5.4029

Max Act: 3.7800. Min Act: -0.0000

Data Index: 1333121 (The Pile)

Max Activating Token Index: 600