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

Dataset: The Pile

Neuron 465 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: 0.4913. Min Range: -0.4913

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1859330 (The Pile)

Max Activating Token Index: 738

Text #1

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4743. Min Act: -0.0000

Data Index: 85141 (The Pile)

Max Activating Token Index: 864

Text #2

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4589. Min Act: -0.0000

Data Index: 666968 (The Pile)

Max Activating Token Index: 702

Text #3

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4913. Min Act: -0.0000

Data Index: 1254425 (The Pile)

Max Activating Token Index: 286

Text #4

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4122. Min Act: -0.0000

Data Index: 805885 (The Pile)

Max Activating Token Index: 764

Text #5

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.3996. Min Act: -0.0000

Data Index: 145460 (The Pile)

Max Activating Token Index: 792

Text #6

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1516097 (The Pile)

Max Activating Token Index: 86

Text #7

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4694. Min Act: -0.0000

Data Index: 1282585 (The Pile)

Max Activating Token Index: 945

Text #8

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4358. Min Act: -0.0000

Data Index: 1072524 (The Pile)

Max Activating Token Index: 419

Text #9

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4195. Min Act: -0.0000

Data Index: 734678 (The Pile)

Max Activating Token Index: 928

Text #10

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4439. Min Act: -0.0000

Data Index: 1188456 (The Pile)

Max Activating Token Index: 498

Text #11

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4412. Min Act: -0.0000

Data Index: 1298430 (The Pile)

Max Activating Token Index: 794

Text #12

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4475. Min Act: -0.0000

Data Index: 972689 (The Pile)

Max Activating Token Index: 898

Text #13

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.3919. Min Act: -0.0000

Data Index: 513547 (The Pile)

Max Activating Token Index: 752

Text #14

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4165. Min Act: -0.0000

Data Index: 1765677 (The Pile)

Max Activating Token Index: 911

Text #15

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4124. Min Act: -0.0000

Data Index: 1847827 (The Pile)

Max Activating Token Index: 150

Text #16

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4085. Min Act: -0.0000

Data Index: 1627674 (The Pile)

Max Activating Token Index: 886

Text #17

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.3858. Min Act: -0.0000

Data Index: 826653 (The Pile)

Max Activating Token Index: 134

Text #18

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.3984. Min Act: -0.0000

Data Index: 1164693 (The Pile)

Max Activating Token Index: 346

Text #19

Max Range: 0.4913. Min Range: -0.4913

Max Act: 0.4061. Min Act: -0.0000

Data Index: 1295888 (The Pile)

Max Activating Token Index: 869