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

Dataset: The Pile

Neuron 4931 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2574. Min Range: -4.2574

Max Act: 4.2574. Min Act: -0.0000

Data Index: 1685122 (The Pile)

Max Activating Token Index: 305

Text #1

Max Range: 4.2574. Min Range: -4.2574

Max Act: 4.0360. Min Act: -0.0000

Data Index: 955858 (The Pile)

Max Activating Token Index: 178

Text #2

Max Range: 4.2574. Min Range: -4.2574

Max Act: 3.7101. Min Act: -0.0000

Data Index: 274044 (The Pile)

Max Activating Token Index: 306

Text #3

Max Range: 4.2574. Min Range: -4.2574

Max Act: 3.7834. Min Act: -0.0000

Data Index: 1683645 (The Pile)

Max Activating Token Index: 277

Text #4

Max Range: 4.2574. Min Range: -4.2574

Max Act: 3.9231. Min Act: -0.0000

Data Index: 328127 (The Pile)

Max Activating Token Index: 381

Text #5

Max Range: 4.2574. Min Range: -4.2574

Max Act: 3.6242. Min Act: -0.0000

Data Index: 705601 (The Pile)

Max Activating Token Index: 397

Text #6

Max Range: 4.2574. Min Range: -4.2574

Max Act: 3.7094. Min Act: -0.0000

Data Index: 1829112 (The Pile)

Max Activating Token Index: 661

Text #7

Max Range: 4.2574. Min Range: -4.2574

Max Act: 3.6602. Min Act: -0.0000

Data Index: 1990877 (The Pile)

Max Activating Token Index: 894

Text #8

Max Range: 4.2574. Min Range: -4.2574

Max Act: 3.9718. Min Act: -0.0000

Data Index: 1743753 (The Pile)

Max Activating Token Index: 451

Text #9

Max Range: 4.2574. Min Range: -4.2574

Max Act: 3.8282. Min Act: -0.0000

Data Index: 1592580 (The Pile)

Max Activating Token Index: 495

Text #10

Max Range: 4.2574. Min Range: -4.2574

Max Act: 3.9197. Min Act: -0.0000

Data Index: 1934995 (The Pile)

Max Activating Token Index: 420

Text #11

Max Range: 4.2574. Min Range: -4.2574

Max Act: 3.5996. Min Act: -0.0000

Data Index: 329741 (The Pile)

Max Activating Token Index: 555

Text #12

Max Range: 4.2574. Min Range: -4.2574

Max Act: 3.7232. Min Act: -0.0000

Data Index: 292248 (The Pile)

Max Activating Token Index: 420

Text #13

Max Range: 4.2574. Min Range: -4.2574

Max Act: 3.0753. Min Act: -0.0000

Data Index: 1728889 (The Pile)

Max Activating Token Index: 999

Text #14

Max Range: 4.2574. Min Range: -4.2574

Max Act: 3.4444. Min Act: -0.0000

Data Index: 489289 (The Pile)

Max Activating Token Index: 1009

Text #15

Max Range: 4.2574. Min Range: -4.2574

Max Act: 3.5229. Min Act: -0.0000

Data Index: 1779968 (The Pile)

Max Activating Token Index: 324

Text #16

Max Range: 4.2574. Min Range: -4.2574

Max Act: 3.4862. Min Act: -0.0000

Data Index: 510755 (The Pile)

Max Activating Token Index: 525

Text #17

Max Range: 4.2574. Min Range: -4.2574

Max Act: 3.4718. Min Act: -0.0000

Data Index: 938634 (The Pile)

Max Activating Token Index: 150

Text #18

Max Range: 4.2574. Min Range: -4.2574

Max Act: 3.3125. Min Act: -0.0000

Data Index: 135294 (The Pile)

Max Activating Token Index: 980

Text #19

Max Range: 4.2574. Min Range: -4.2574

Max Act: 3.4760. Min Act: -0.0000

Data Index: 757283 (The Pile)

Max Activating Token Index: 863