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

Dataset: The Pile

Neuron 3508 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3862. Min Act: -0.0000

Data Index: 1835900 (The Pile)

Max Activating Token Index: 297

Text #1

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3844. Min Act: -0.0000

Data Index: 307853 (The Pile)

Max Activating Token Index: 343

Text #2

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3840. Min Act: -0.0000

Data Index: 670296 (The Pile)

Max Activating Token Index: 381

Text #3

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3715. Min Act: -0.0000

Data Index: 765929 (The Pile)

Max Activating Token Index: 147

Text #4

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3679. Min Act: -0.0000

Data Index: 787751 (The Pile)

Max Activating Token Index: 129

Text #5

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3822. Min Act: -0.0000

Data Index: 289345 (The Pile)

Max Activating Token Index: 143

Text #6

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3595. Min Act: -0.0000

Data Index: 990608 (The Pile)

Max Activating Token Index: 204

Text #7

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3679. Min Act: -0.0000

Data Index: 1385923 (The Pile)

Max Activating Token Index: 140

Text #8

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3652. Min Act: -0.0000

Data Index: 308448 (The Pile)

Max Activating Token Index: 165

Text #9

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3651. Min Act: -0.0000

Data Index: 1081924 (The Pile)

Max Activating Token Index: 168

Text #10

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3562. Min Act: -0.0000

Data Index: 737587 (The Pile)

Max Activating Token Index: 263

Text #11

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3340. Min Act: -0.0000

Data Index: 102737 (The Pile)

Max Activating Token Index: 244

Text #12

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3000. Min Act: -0.0000

Data Index: 207533 (The Pile)

Max Activating Token Index: 538

Text #13

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2901. Min Act: -0.0000

Data Index: 1372218 (The Pile)

Max Activating Token Index: 533

Text #14

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.3079. Min Act: -0.0000

Data Index: 853784 (The Pile)

Max Activating Token Index: 479

Text #15

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2893. Min Act: -0.0000

Data Index: 235022 (The Pile)

Max Activating Token Index: 321

Text #16

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2902. Min Act: -0.0000

Data Index: 1607608 (The Pile)

Max Activating Token Index: 255

Text #17

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2887. Min Act: -0.0000

Data Index: 786890 (The Pile)

Max Activating Token Index: 241

Text #18

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2824. Min Act: -0.0000

Data Index: 455388 (The Pile)

Max Activating Token Index: 273

Text #19

Max Range: 0.3862. Min Range: -0.3862

Max Act: 0.2710. Min Act: -0.0000

Data Index: 134144 (The Pile)

Max Activating Token Index: 288