Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2672 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.7734. Min Act: -0.0000

Data Index: 1014167 (The Pile)

Max Activating Token Index: 433

Text #1

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.6036. Min Act: -0.0000

Data Index: 1513880 (The Pile)

Max Activating Token Index: 884

Text #2

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5674. Min Act: -0.0000

Data Index: 1509323 (The Pile)

Max Activating Token Index: 892

Text #3

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5214. Min Act: 0.0000

Data Index: 1197290 (The Pile)

Max Activating Token Index: 341

Text #4

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1538899 (The Pile)

Max Activating Token Index: 612

Text #5

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4932. Min Act: -0.0000

Data Index: 951539 (The Pile)

Max Activating Token Index: 668

Text #6

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5563. Min Act: -0.0000

Data Index: 299216 (The Pile)

Max Activating Token Index: 608

Text #7

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4889. Min Act: 0.0000

Data Index: 740821 (The Pile)

Max Activating Token Index: 1005

Text #8

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4846. Min Act: 0.0000

Data Index: 1445851 (The Pile)

Max Activating Token Index: 442

Text #9

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5288. Min Act: -0.0000

Data Index: 411893 (The Pile)

Max Activating Token Index: 721

Text #10

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4005. Min Act: -0.0000

Data Index: 1205148 (The Pile)

Max Activating Token Index: 746

Text #11

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4744. Min Act: 0.0000

Data Index: 1696826 (The Pile)

Max Activating Token Index: 535

Text #12

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4838. Min Act: -0.0000

Data Index: 1779510 (The Pile)

Max Activating Token Index: 881

Text #13

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4675. Min Act: -0.0000

Data Index: 818813 (The Pile)

Max Activating Token Index: 356

Text #14

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5013. Min Act: -0.0000

Data Index: 560744 (The Pile)

Max Activating Token Index: 396

Text #15

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4390. Min Act: -0.0000

Data Index: 50958 (The Pile)

Max Activating Token Index: 323

Text #16

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.5050. Min Act: 0.0000

Data Index: 1682801 (The Pile)

Max Activating Token Index: 827

Text #17

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1209201 (The Pile)

Max Activating Token Index: 953

Text #18

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4301. Min Act: -0.0000

Data Index: 765511 (The Pile)

Max Activating Token Index: 406

Text #19

Max Range: 0.7734. Min Range: -0.7734

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1403324 (The Pile)

Max Activating Token Index: 191