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

Dataset: The Pile

Neuron 3700 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.3017. Min Act: -0.0000

Data Index: 723802 (The Pile)

Max Activating Token Index: 963

Text #1

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.0913. Min Act: -0.0000

Data Index: 1646631 (The Pile)

Max Activating Token Index: 647

Text #2

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.2224. Min Act: -0.0000

Data Index: 285158 (The Pile)

Max Activating Token Index: 210

Text #3

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.2017. Min Act: -0.0000

Data Index: 703799 (The Pile)

Max Activating Token Index: 378

Text #4

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.0681. Min Act: -0.0000

Data Index: 145363 (The Pile)

Max Activating Token Index: 369

Text #5

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.0607. Min Act: -0.0000

Data Index: 797430 (The Pile)

Max Activating Token Index: 576

Text #6

Max Range: 1.3017. Min Range: -1.3017

Max Act: 0.9071. Min Act: -0.0000

Data Index: 1697296 (The Pile)

Max Activating Token Index: 716

Text #7

Max Range: 1.3017. Min Range: -1.3017

Max Act: 0.9632. Min Act: -0.0000

Data Index: 1160652 (The Pile)

Max Activating Token Index: 147

Text #8

Max Range: 1.3017. Min Range: -1.3017

Max Act: 0.9355. Min Act: -0.0000

Data Index: 917250 (The Pile)

Max Activating Token Index: 300

Text #9

Max Range: 1.3017. Min Range: -1.3017

Max Act: 1.0756. Min Act: -0.0000

Data Index: 1645085 (The Pile)

Max Activating Token Index: 896

Text #10

Max Range: 1.3017. Min Range: -1.3017

Max Act: 0.9132. Min Act: -0.0000

Data Index: 6790 (The Pile)

Max Activating Token Index: 63

Text #11

Max Range: 1.3017. Min Range: -1.3017

Max Act: 0.8840. Min Act: -0.0000

Data Index: 468790 (The Pile)

Max Activating Token Index: 100

Text #12

Max Range: 1.3017. Min Range: -1.3017

Max Act: 0.8508. Min Act: -0.0000

Data Index: 271422 (The Pile)

Max Activating Token Index: 396

Text #13

Max Range: 1.3017. Min Range: -1.3017

Max Act: 0.8913. Min Act: -0.0000

Data Index: 1886462 (The Pile)

Max Activating Token Index: 293

Text #14

Max Range: 1.3017. Min Range: -1.3017

Max Act: 0.8812. Min Act: -0.0000

Data Index: 585049 (The Pile)

Max Activating Token Index: 561

Text #15

Max Range: 1.3017. Min Range: -1.3017

Max Act: 0.8379. Min Act: -0.0000

Data Index: 600360 (The Pile)

Max Activating Token Index: 553

Text #16

Max Range: 1.3017. Min Range: -1.3017

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1022840 (The Pile)

Max Activating Token Index: 141

Text #17

Max Range: 1.3017. Min Range: -1.3017

Max Act: 0.8378. Min Act: -0.0000

Data Index: 1551382 (The Pile)

Max Activating Token Index: 792

Text #18

Max Range: 1.3017. Min Range: -1.3017

Max Act: 0.8338. Min Act: -0.0000

Data Index: 1364348 (The Pile)

Max Activating Token Index: 674

Text #19

Max Range: 1.3017. Min Range: -1.3017

Max Act: 0.8326. Min Act: -0.0000

Data Index: 1085763 (The Pile)

Max Activating Token Index: 230