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

Dataset: The Pile

Neuron 15 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: 0.5761. Min Range: -0.5761

Max Act: 0.5761. Min Act: -0.0000

Data Index: 463820 (The Pile)

Max Activating Token Index: 768

Text #1

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1973524 (The Pile)

Max Activating Token Index: 333

Text #2

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.4807. Min Act: -0.0000

Data Index: 1630535 (The Pile)

Max Activating Token Index: 850

Text #3

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.4182. Min Act: -0.0000

Data Index: 518823 (The Pile)

Max Activating Token Index: 808

Text #4

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.4444. Min Act: -0.0000

Data Index: 181417 (The Pile)

Max Activating Token Index: 853

Text #5

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.4255. Min Act: -0.0000

Data Index: 866816 (The Pile)

Max Activating Token Index: 534

Text #6

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.4230. Min Act: -0.0000

Data Index: 1864148 (The Pile)

Max Activating Token Index: 97

Text #7

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1299906 (The Pile)

Max Activating Token Index: 561

Text #8

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.3930. Min Act: -0.0000

Data Index: 556944 (The Pile)

Max Activating Token Index: 947

Text #9

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.4037. Min Act: -0.0000

Data Index: 591214 (The Pile)

Max Activating Token Index: 911

Text #10

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.4327. Min Act: -0.0000

Data Index: 944458 (The Pile)

Max Activating Token Index: 113

Text #11

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.4029. Min Act: -0.0000

Data Index: 1184628 (The Pile)

Max Activating Token Index: 174

Text #12

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.4005. Min Act: -0.0000

Data Index: 710493 (The Pile)

Max Activating Token Index: 292

Text #13

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.4124. Min Act: -0.0000

Data Index: 734343 (The Pile)

Max Activating Token Index: 666

Text #14

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.3796. Min Act: -0.0000

Data Index: 488454 (The Pile)

Max Activating Token Index: 555

Text #15

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.3834. Min Act: -0.0000

Data Index: 1722456 (The Pile)

Max Activating Token Index: 700

Text #16

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1458911 (The Pile)

Max Activating Token Index: 636

Text #17

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.3499. Min Act: 0.0000

Data Index: 1687517 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.3839. Min Act: -0.0000

Data Index: 230032 (The Pile)

Max Activating Token Index: 746

Text #19

Max Range: 0.5761. Min Range: -0.5761

Max Act: 0.3553. Min Act: -0.0000

Data Index: 612366 (The Pile)

Max Activating Token Index: 589