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

Dataset: The Pile

Neuron 1473 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: 6.5833. Min Range: -6.5833

Max Act: 5.9664. Min Act: -0.0000

Data Index: 1132219 (The Pile)

Max Activating Token Index: 652

Text #1

Max Range: 6.5833. Min Range: -6.5833

Max Act: 6.3346. Min Act: -0.0000

Data Index: 852333 (The Pile)

Max Activating Token Index: 501

Text #2

Max Range: 6.5833. Min Range: -6.5833

Max Act: 6.0053. Min Act: -0.0000

Data Index: 1999167 (The Pile)

Max Activating Token Index: 444

Text #3

Max Range: 6.5833. Min Range: -6.5833

Max Act: 6.2917. Min Act: -0.0000

Data Index: 685331 (The Pile)

Max Activating Token Index: 391

Text #4

Max Range: 6.5833. Min Range: -6.5833

Max Act: 6.5833. Min Act: -0.0000

Data Index: 15681 (The Pile)

Max Activating Token Index: 692

Text #5

Max Range: 6.5833. Min Range: -6.5833

Max Act: 6.1482. Min Act: -0.0000

Data Index: 1001808 (The Pile)

Max Activating Token Index: 275

Text #6

Max Range: 6.5833. Min Range: -6.5833

Max Act: 5.0097. Min Act: -0.0000

Data Index: 1608270 (The Pile)

Max Activating Token Index: 863

Text #7

Max Range: 6.5833. Min Range: -6.5833

Max Act: 6.0207. Min Act: -0.0000

Data Index: 181195 (The Pile)

Max Activating Token Index: 507

Text #8

Max Range: 6.5833. Min Range: -6.5833

Max Act: 6.0027. Min Act: -0.0000

Data Index: 346368 (The Pile)

Max Activating Token Index: 454

Text #9

Max Range: 6.5833. Min Range: -6.5833

Max Act: 5.9072. Min Act: -0.0000

Data Index: 131390 (The Pile)

Max Activating Token Index: 342

Text #10

Max Range: 6.5833. Min Range: -6.5833

Max Act: 5.9335. Min Act: -0.0000

Data Index: 995385 (The Pile)

Max Activating Token Index: 283

Text #11

Max Range: 6.5833. Min Range: -6.5833

Max Act: 5.1351. Min Act: -0.0000

Data Index: 1347769 (The Pile)

Max Activating Token Index: 660

Text #12

Max Range: 6.5833. Min Range: -6.5833

Max Act: 5.4848. Min Act: -0.0000

Data Index: 118746 (The Pile)

Max Activating Token Index: 243

Text #13

Max Range: 6.5833. Min Range: -6.5833

Max Act: 5.5870. Min Act: -0.0000

Data Index: 220975 (The Pile)

Max Activating Token Index: 553

Text #14

Max Range: 6.5833. Min Range: -6.5833

Max Act: 5.8092. Min Act: -0.0000

Data Index: 368306 (The Pile)

Max Activating Token Index: 810

Text #15

Max Range: 6.5833. Min Range: -6.5833

Max Act: 5.6706. Min Act: -0.0000

Data Index: 693753 (The Pile)

Max Activating Token Index: 147

Text #16

Max Range: 6.5833. Min Range: -6.5833

Max Act: 5.6893. Min Act: -0.0000

Data Index: 1198191 (The Pile)

Max Activating Token Index: 133

Text #17

Max Range: 6.5833. Min Range: -6.5833

Max Act: 5.5878. Min Act: -0.0000

Data Index: 1511029 (The Pile)

Max Activating Token Index: 610

Text #18

Max Range: 6.5833. Min Range: -6.5833

Max Act: 5.9397. Min Act: -0.0000

Data Index: 1191946 (The Pile)

Max Activating Token Index: 495

Text #19

Max Range: 6.5833. Min Range: -6.5833

Max Act: 5.0044. Min Act: -0.0000

Data Index: 266828 (The Pile)

Max Activating Token Index: 267