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

Dataset: The Pile

Neuron 2629 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: 1.4886. Min Range: -1.4886

Max Act: 1.4886. Min Act: -0.0000

Data Index: 1652956 (The Pile)

Max Activating Token Index: 384

Text #1

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.4816. Min Act: -0.0000

Data Index: 786465 (The Pile)

Max Activating Token Index: 16

Text #2

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.2751. Min Act: -0.0000

Data Index: 1282293 (The Pile)

Max Activating Token Index: 545

Text #3

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.2698. Min Act: -0.0000

Data Index: 275009 (The Pile)

Max Activating Token Index: 587

Text #4

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.2018. Min Act: -0.0000

Data Index: 977390 (The Pile)

Max Activating Token Index: 734

Text #5

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.2223. Min Act: -0.0000

Data Index: 778990 (The Pile)

Max Activating Token Index: 278

Text #6

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.0619. Min Act: -0.0000

Data Index: 832471 (The Pile)

Max Activating Token Index: 350

Text #7

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.1179. Min Act: -0.0000

Data Index: 886452 (The Pile)

Max Activating Token Index: 416

Text #8

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.1190. Min Act: -0.0000

Data Index: 49094 (The Pile)

Max Activating Token Index: 657

Text #9

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.0617. Min Act: -0.0000

Data Index: 1283242 (The Pile)

Max Activating Token Index: 641

Text #10

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.0076. Min Act: -0.0000

Data Index: 212432 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.0727. Min Act: -0.0000

Data Index: 1147176 (The Pile)

Max Activating Token Index: 701

Text #12

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.1370. Min Act: -0.0000

Data Index: 1560088 (The Pile)

Max Activating Token Index: 944

Text #13

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.0400. Min Act: -0.0000

Data Index: 358777 (The Pile)

Max Activating Token Index: 673

Text #14

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.0133. Min Act: -0.0000

Data Index: 1866922 (The Pile)

Max Activating Token Index: 807

Text #15

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.0233. Min Act: -0.0000

Data Index: 690639 (The Pile)

Max Activating Token Index: 400

Text #16

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.0241. Min Act: -0.0000

Data Index: 904592 (The Pile)

Max Activating Token Index: 36

Text #17

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.0165. Min Act: -0.0000

Data Index: 430786 (The Pile)

Max Activating Token Index: 738

Text #18

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.0187. Min Act: -0.0000

Data Index: 639151 (The Pile)

Max Activating Token Index: 479

Text #19

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.0137. Min Act: -0.0000

Data Index: 807020 (The Pile)

Max Activating Token Index: 458