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

Dataset: The Pile

Neuron 1127 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: 0.7355. Min Range: -0.7355

Max Act: 0.7355. Min Act: -0.0000

Data Index: 1807604 (The Pile)

Max Activating Token Index: 159

Text #1

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6748. Min Act: -0.0000

Data Index: 512246 (The Pile)

Max Activating Token Index: 570

Text #2

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6235. Min Act: -0.0000

Data Index: 323601 (The Pile)

Max Activating Token Index: 295

Text #3

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6798. Min Act: -0.0000

Data Index: 1435551 (The Pile)

Max Activating Token Index: 583

Text #4

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6553. Min Act: -0.0000

Data Index: 1358954 (The Pile)

Max Activating Token Index: 106

Text #5

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6358. Min Act: -0.0000

Data Index: 1550308 (The Pile)

Max Activating Token Index: 520

Text #6

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6989. Min Act: -0.0000

Data Index: 1912484 (The Pile)

Max Activating Token Index: 925

Text #7

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6129. Min Act: -0.0000

Data Index: 1196086 (The Pile)

Max Activating Token Index: 66

Text #8

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.5917. Min Act: -0.0000

Data Index: 1491144 (The Pile)

Max Activating Token Index: 80

Text #9

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1945660 (The Pile)

Max Activating Token Index: 900

Text #10

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.5860. Min Act: -0.0000

Data Index: 1631566 (The Pile)

Max Activating Token Index: 448

Text #11

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6089. Min Act: -0.0000

Data Index: 776553 (The Pile)

Max Activating Token Index: 780

Text #12

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6078. Min Act: -0.0000

Data Index: 1890204 (The Pile)

Max Activating Token Index: 195

Text #13

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.5943. Min Act: -0.0000

Data Index: 85147 (The Pile)

Max Activating Token Index: 349

Text #14

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.5750. Min Act: -0.0000

Data Index: 900938 (The Pile)

Max Activating Token Index: 537

Text #15

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.6059. Min Act: -0.0000

Data Index: 1823748 (The Pile)

Max Activating Token Index: 874

Text #16

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1373292 (The Pile)

Max Activating Token Index: 401

Text #17

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.5668. Min Act: -0.0000

Data Index: 159756 (The Pile)

Max Activating Token Index: 423

Text #18

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.5306. Min Act: -0.0000

Data Index: 234454 (The Pile)

Max Activating Token Index: 484

Text #19

Max Range: 0.7355. Min Range: -0.7355

Max Act: 0.5459. Min Act: -0.0000

Data Index: 342160 (The Pile)

Max Activating Token Index: 977