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

Dataset: The Pile

Neuron 472 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: 0.3791. Min Range: -0.3791

Max Act: 0.3791. Min Act: -0.0000

Data Index: 1546397 (The Pile)

Max Activating Token Index: 673

Text #1

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.2703. Min Act: -0.0000

Data Index: 1092462 (The Pile)

Max Activating Token Index: 880

Text #2

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.3065. Min Act: -0.0000

Data Index: 854529 (The Pile)

Max Activating Token Index: 201

Text #3

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.2820. Min Act: -0.0000

Data Index: 746288 (The Pile)

Max Activating Token Index: 846

Text #4

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.2966. Min Act: -0.0000

Data Index: 301960 (The Pile)

Max Activating Token Index: 839

Text #5

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1338101 (The Pile)

Max Activating Token Index: 915

Text #6

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.2254. Min Act: -0.0000

Data Index: 640605 (The Pile)

Max Activating Token Index: 513

Text #7

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.2640. Min Act: -0.0000

Data Index: 1232019 (The Pile)

Max Activating Token Index: 669

Text #8

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.1812. Min Act: -0.0000

Data Index: 645310 (The Pile)

Max Activating Token Index: 817

Text #9

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1015029 (The Pile)

Max Activating Token Index: 354

Text #10

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.2046. Min Act: -0.0000

Data Index: 250557 (The Pile)

Max Activating Token Index: 153

Text #11

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1178817 (The Pile)

Max Activating Token Index: 698

Text #12

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.2114. Min Act: -0.0000

Data Index: 1982798 (The Pile)

Max Activating Token Index: 397

Text #13

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.1945. Min Act: -0.0000

Data Index: 1933609 (The Pile)

Max Activating Token Index: 209

Text #14

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.1456. Min Act: -0.0000

Data Index: 1846265 (The Pile)

Max Activating Token Index: 1016

Text #15

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.1981. Min Act: -0.0000

Data Index: 387077 (The Pile)

Max Activating Token Index: 283

Text #16

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.1661. Min Act: -0.0000

Data Index: 1301542 (The Pile)

Max Activating Token Index: 394

Text #17

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.1614. Min Act: -0.0000

Data Index: 1588658 (The Pile)

Max Activating Token Index: 661

Text #18

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.1578. Min Act: -0.0000

Data Index: 1241098 (The Pile)

Max Activating Token Index: 212

Text #19

Max Range: 0.3791. Min Range: -0.3791

Max Act: 0.1694. Min Act: -0.0000

Data Index: 1184104 (The Pile)

Max Activating Token Index: 795