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

Dataset: The Pile

Neuron 2719 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1617. Min Range: -1.1617

Max Act: 1.1617. Min Act: -0.0000

Data Index: 388206 (The Pile)

Max Activating Token Index: 731

Text #1

Max Range: 1.1617. Min Range: -1.1617

Max Act: 1.0569. Min Act: -0.0000

Data Index: 789185 (The Pile)

Max Activating Token Index: 645

Text #2

Max Range: 1.1617. Min Range: -1.1617

Max Act: 1.0877. Min Act: -0.0000

Data Index: 1805909 (The Pile)

Max Activating Token Index: 713

Text #3

Max Range: 1.1617. Min Range: -1.1617

Max Act: 0.9438. Min Act: -0.0000

Data Index: 883848 (The Pile)

Max Activating Token Index: 465

Text #4

Max Range: 1.1617. Min Range: -1.1617

Max Act: 1.0766. Min Act: -0.0000

Data Index: 1791051 (The Pile)

Max Activating Token Index: 849

Text #5

Max Range: 1.1617. Min Range: -1.1617

Max Act: 1.0542. Min Act: -0.0000

Data Index: 1042384 (The Pile)

Max Activating Token Index: 973

Text #6

Max Range: 1.1617. Min Range: -1.1617

Max Act: 1.0089. Min Act: -0.0000

Data Index: 493158 (The Pile)

Max Activating Token Index: 167

Text #7

Max Range: 1.1617. Min Range: -1.1617

Max Act: 1.0036. Min Act: -0.0000

Data Index: 167946 (The Pile)

Max Activating Token Index: 714

Text #8

Max Range: 1.1617. Min Range: -1.1617

Max Act: 0.9720. Min Act: -0.0000

Data Index: 835703 (The Pile)

Max Activating Token Index: 193

Text #9

Max Range: 1.1617. Min Range: -1.1617

Max Act: 0.9539. Min Act: -0.0000

Data Index: 1699374 (The Pile)

Max Activating Token Index: 87

Text #10

Max Range: 1.1617. Min Range: -1.1617

Max Act: 0.8521. Min Act: -0.0000

Data Index: 456798 (The Pile)

Max Activating Token Index: 617

Text #11

Max Range: 1.1617. Min Range: -1.1617

Max Act: 0.9193. Min Act: -0.0000

Data Index: 1127027 (The Pile)

Max Activating Token Index: 264

Text #12

Max Range: 1.1617. Min Range: -1.1617

Max Act: 1.0225. Min Act: -0.0000

Data Index: 800600 (The Pile)

Max Activating Token Index: 878

Text #13

Max Range: 1.1617. Min Range: -1.1617

Max Act: 1.0744. Min Act: -0.0000

Data Index: 206407 (The Pile)

Max Activating Token Index: 627

Text #14

Max Range: 1.1617. Min Range: -1.1617

Max Act: 0.9439. Min Act: -0.0000

Data Index: 701674 (The Pile)

Max Activating Token Index: 258

Text #15

Max Range: 1.1617. Min Range: -1.1617

Max Act: 0.9606. Min Act: -0.0000

Data Index: 1389138 (The Pile)

Max Activating Token Index: 93

Text #16

Max Range: 1.1617. Min Range: -1.1617

Max Act: 0.9277. Min Act: -0.0000

Data Index: 838696 (The Pile)

Max Activating Token Index: 540

Text #17

Max Range: 1.1617. Min Range: -1.1617

Max Act: 0.8686. Min Act: -0.0000

Data Index: 1451359 (The Pile)

Max Activating Token Index: 161

Text #18

Max Range: 1.1617. Min Range: -1.1617

Max Act: 0.9448. Min Act: -0.0000

Data Index: 198491 (The Pile)

Max Activating Token Index: 697

Text #19

Max Range: 1.1617. Min Range: -1.1617

Max Act: 0.8638. Min Act: -0.0000

Data Index: 480051 (The Pile)

Max Activating Token Index: 654