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

Dataset: The Pile

Neuron 1497 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: 3.1750. Min Range: -3.1750

Max Act: 3.1750. Min Act: -0.0000

Data Index: 1123622 (The Pile)

Max Activating Token Index: 230

Text #1

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.8537. Min Act: -0.0000

Data Index: 983554 (The Pile)

Max Activating Token Index: 196

Text #2

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.9770. Min Act: -0.0000

Data Index: 802714 (The Pile)

Max Activating Token Index: 360

Text #3

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.9554. Min Act: -0.0000

Data Index: 696911 (The Pile)

Max Activating Token Index: 824

Text #4

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.7542. Min Act: -0.0000

Data Index: 210460 (The Pile)

Max Activating Token Index: 382

Text #5

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.8666. Min Act: -0.0000

Data Index: 583081 (The Pile)

Max Activating Token Index: 74

Text #6

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.9647. Min Act: -0.0000

Data Index: 1729060 (The Pile)

Max Activating Token Index: 222

Text #7

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.8251. Min Act: -0.0000

Data Index: 716853 (The Pile)

Max Activating Token Index: 754

Text #8

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.6820. Min Act: -0.0000

Data Index: 1011468 (The Pile)

Max Activating Token Index: 167

Text #9

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.6962. Min Act: -0.0000

Data Index: 936193 (The Pile)

Max Activating Token Index: 145

Text #10

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.7913. Min Act: -0.0000

Data Index: 765296 (The Pile)

Max Activating Token Index: 276

Text #11

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.7694. Min Act: -0.0000

Data Index: 1908503 (The Pile)

Max Activating Token Index: 918

Text #12

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.7061. Min Act: -0.0000

Data Index: 512381 (The Pile)

Max Activating Token Index: 544

Text #13

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.6782. Min Act: -0.0000

Data Index: 367545 (The Pile)

Max Activating Token Index: 876

Text #14

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.6803. Min Act: -0.0000

Data Index: 266253 (The Pile)

Max Activating Token Index: 803

Text #15

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.7904. Min Act: -0.0000

Data Index: 124425 (The Pile)

Max Activating Token Index: 781

Text #16

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.6538. Min Act: -0.0000

Data Index: 31670 (The Pile)

Max Activating Token Index: 686

Text #17

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.7744. Min Act: -0.0000

Data Index: 378466 (The Pile)

Max Activating Token Index: 820

Text #18

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.7730. Min Act: -0.0000

Data Index: 1563065 (The Pile)

Max Activating Token Index: 253

Text #19

Max Range: 3.1750. Min Range: -3.1750

Max Act: 2.6254. Min Act: -0.0000

Data Index: 403373 (The Pile)

Max Activating Token Index: 43