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

Dataset: The Pile

Neuron 2106 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5659. Min Act: -0.0000

Data Index: 1025861 (The Pile)

Max Activating Token Index: 632

Text #1

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5833. Min Act: -0.0000

Data Index: 1719970 (The Pile)

Max Activating Token Index: 575

Text #2

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5626. Min Act: -0.0000

Data Index: 1346171 (The Pile)

Max Activating Token Index: 297

Text #3

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5695. Min Act: -0.0000

Data Index: 49641 (The Pile)

Max Activating Token Index: 334

Text #4

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5742. Min Act: -0.0000

Data Index: 706661 (The Pile)

Max Activating Token Index: 450

Text #5

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5165. Min Act: -0.0000

Data Index: 1440750 (The Pile)

Max Activating Token Index: 399

Text #6

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.6736. Min Act: -0.0000

Data Index: 1832261 (The Pile)

Max Activating Token Index: 270

Text #7

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4646. Min Act: -0.0000

Data Index: 910041 (The Pile)

Max Activating Token Index: 808

Text #8

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4658. Min Act: -0.0000

Data Index: 426758 (The Pile)

Max Activating Token Index: 139

Text #9

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4542. Min Act: -0.0000

Data Index: 1710658 (The Pile)

Max Activating Token Index: 897

Text #10

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1900433 (The Pile)

Max Activating Token Index: 544

Text #11

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4786. Min Act: -0.0000

Data Index: 995978 (The Pile)

Max Activating Token Index: 104

Text #12

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5415. Min Act: -0.0000

Data Index: 910986 (The Pile)

Max Activating Token Index: 708

Text #13

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1742848 (The Pile)

Max Activating Token Index: 151

Text #14

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4905. Min Act: -0.0000

Data Index: 1652183 (The Pile)

Max Activating Token Index: 466

Text #15

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4961. Min Act: -0.0000

Data Index: 360872 (The Pile)

Max Activating Token Index: 973

Text #16

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4875. Min Act: -0.0000

Data Index: 1380754 (The Pile)

Max Activating Token Index: 345

Text #17

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4879. Min Act: -0.0000

Data Index: 196577 (The Pile)

Max Activating Token Index: 847

Text #18

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4843. Min Act: -0.0000

Data Index: 1201551 (The Pile)

Max Activating Token Index: 216

Text #19

Max Range: 0.6736. Min Range: -0.6736

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1049379 (The Pile)

Max Activating Token Index: 627