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

Dataset: The Pile

Neuron 3081 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.2901. Min Act: -0.0000

Data Index: 1618318 (The Pile)

Max Activating Token Index: 263

Text #1

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.0698. Min Act: -0.0000

Data Index: 1663961 (The Pile)

Max Activating Token Index: 867

Text #2

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.0420. Min Act: -0.0000

Data Index: 1864011 (The Pile)

Max Activating Token Index: 769

Text #3

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.1370. Min Act: -0.0000

Data Index: 1969571 (The Pile)

Max Activating Token Index: 982

Text #4

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.0612. Min Act: -0.0000

Data Index: 1402347 (The Pile)

Max Activating Token Index: 997

Text #5

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.9722. Min Act: -0.0000

Data Index: 1320958 (The Pile)

Max Activating Token Index: 243

Text #6

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.0734. Min Act: -0.0000

Data Index: 1308514 (The Pile)

Max Activating Token Index: 563

Text #7

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.9876. Min Act: -0.0000

Data Index: 1740258 (The Pile)

Max Activating Token Index: 622

Text #8

Max Range: 1.2901. Min Range: -1.2901

Max Act: 1.0191. Min Act: -0.0000

Data Index: 1648355 (The Pile)

Max Activating Token Index: 535

Text #9

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.9573. Min Act: -0.0000

Data Index: 625008 (The Pile)

Max Activating Token Index: 382

Text #10

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.9353. Min Act: -0.0000

Data Index: 1502285 (The Pile)

Max Activating Token Index: 442

Text #11

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.9523. Min Act: -0.0000

Data Index: 230887 (The Pile)

Max Activating Token Index: 115

Text #12

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.9497. Min Act: -0.0000

Data Index: 1295735 (The Pile)

Max Activating Token Index: 349

Text #13

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.9203. Min Act: -0.0000

Data Index: 50300 (The Pile)

Max Activating Token Index: 177

Text #14

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.9527. Min Act: -0.0000

Data Index: 381581 (The Pile)

Max Activating Token Index: 600

Text #15

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.8977. Min Act: -0.0000

Data Index: 966170 (The Pile)

Max Activating Token Index: 389

Text #16

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.9171. Min Act: -0.0000

Data Index: 1609689 (The Pile)

Max Activating Token Index: 193

Text #17

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.8120. Min Act: -0.0000

Data Index: 690951 (The Pile)

Max Activating Token Index: 493

Text #18

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.8777. Min Act: -0.0000

Data Index: 674919 (The Pile)

Max Activating Token Index: 854

Text #19

Max Range: 1.2901. Min Range: -1.2901

Max Act: 0.9483. Min Act: -0.0000

Data Index: 1516744 (The Pile)

Max Activating Token Index: 673