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

Dataset: The Pile

Neuron 2401 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: 4.0220. Min Range: -4.0220

Max Act: 3.8564. Min Act: -0.0000

Data Index: 1577008 (The Pile)

Max Activating Token Index: 847

Text #1

Max Range: 4.0220. Min Range: -4.0220

Max Act: 4.0220. Min Act: -0.0000

Data Index: 791389 (The Pile)

Max Activating Token Index: 451

Text #2

Max Range: 4.0220. Min Range: -4.0220

Max Act: 3.8265. Min Act: -0.0000

Data Index: 828822 (The Pile)

Max Activating Token Index: 438

Text #3

Max Range: 4.0220. Min Range: -4.0220

Max Act: 3.8322. Min Act: -0.0000

Data Index: 325252 (The Pile)

Max Activating Token Index: 806

Text #4

Max Range: 4.0220. Min Range: -4.0220

Max Act: 3.6209. Min Act: -0.0000

Data Index: 960179 (The Pile)

Max Activating Token Index: 854

Text #5

Max Range: 4.0220. Min Range: -4.0220

Max Act: 3.6964. Min Act: -0.0000

Data Index: 898498 (The Pile)

Max Activating Token Index: 877

Text #6

Max Range: 4.0220. Min Range: -4.0220

Max Act: 3.7014. Min Act: -0.0000

Data Index: 490333 (The Pile)

Max Activating Token Index: 512

Text #7

Max Range: 4.0220. Min Range: -4.0220

Max Act: 3.6225. Min Act: -0.0000

Data Index: 911899 (The Pile)

Max Activating Token Index: 879

Text #8

Max Range: 4.0220. Min Range: -4.0220

Max Act: 3.6648. Min Act: -0.0000

Data Index: 844796 (The Pile)

Max Activating Token Index: 778

Text #9

Max Range: 4.0220. Min Range: -4.0220

Max Act: 3.2676. Min Act: -0.0000

Data Index: 478416 (The Pile)

Max Activating Token Index: 58

Text #10

Max Range: 4.0220. Min Range: -4.0220

Max Act: 3.4200. Min Act: -0.0000

Data Index: 772962 (The Pile)

Max Activating Token Index: 408

Text #11

Max Range: 4.0220. Min Range: -4.0220

Max Act: 3.4016. Min Act: -0.0000

Data Index: 727193 (The Pile)

Max Activating Token Index: 528

Text #12

Max Range: 4.0220. Min Range: -4.0220

Max Act: 3.2604. Min Act: -0.0000

Data Index: 1333001 (The Pile)

Max Activating Token Index: 739

Text #13

Max Range: 4.0220. Min Range: -4.0220

Max Act: 3.5312. Min Act: -0.0000

Data Index: 1198154 (The Pile)

Max Activating Token Index: 226

Text #14

Max Range: 4.0220. Min Range: -4.0220

Max Act: 3.3653. Min Act: -0.0000

Data Index: 1122495 (The Pile)

Max Activating Token Index: 700

Text #15

Max Range: 4.0220. Min Range: -4.0220

Max Act: 3.1739. Min Act: -0.0000

Data Index: 463980 (The Pile)

Max Activating Token Index: 563

Text #16

Max Range: 4.0220. Min Range: -4.0220

Max Act: 3.6467. Min Act: -0.0000

Data Index: 1077712 (The Pile)

Max Activating Token Index: 648

Text #17

Max Range: 4.0220. Min Range: -4.0220

Max Act: 3.3145. Min Act: -0.0000

Data Index: 168205 (The Pile)

Max Activating Token Index: 644

Text #18

Max Range: 4.0220. Min Range: -4.0220

Max Act: 3.1685. Min Act: -0.0000

Data Index: 1870965 (The Pile)

Max Activating Token Index: 651

Text #19

Max Range: 4.0220. Min Range: -4.0220

Max Act: 3.2956. Min Act: -0.0000

Data Index: 211555 (The Pile)

Max Activating Token Index: 538