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

Dataset: The Pile

Neuron 1566 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: 1.1600. Min Range: -1.1600

Max Act: 1.1600. Min Act: -0.0000

Data Index: 1485080 (The Pile)

Max Activating Token Index: 343

Text #1

Max Range: 1.1600. Min Range: -1.1600

Max Act: 1.0677. Min Act: -0.0000

Data Index: 1698473 (The Pile)

Max Activating Token Index: 337

Text #2

Max Range: 1.1600. Min Range: -1.1600

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1002572 (The Pile)

Max Activating Token Index: 397

Text #3

Max Range: 1.1600. Min Range: -1.1600

Max Act: 1.0128. Min Act: -0.0000

Data Index: 1401457 (The Pile)

Max Activating Token Index: 369

Text #4

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9513. Min Act: -0.0000

Data Index: 489457 (The Pile)

Max Activating Token Index: 590

Text #5

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9717. Min Act: -0.0000

Data Index: 1471355 (The Pile)

Max Activating Token Index: 342

Text #6

Max Range: 1.1600. Min Range: -1.1600

Max Act: 1.0099. Min Act: -0.0000

Data Index: 1393786 (The Pile)

Max Activating Token Index: 713

Text #7

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9811. Min Act: -0.0000

Data Index: 243843 (The Pile)

Max Activating Token Index: 495

Text #8

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9389. Min Act: -0.0000

Data Index: 499430 (The Pile)

Max Activating Token Index: 460

Text #9

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8827. Min Act: -0.0000

Data Index: 315765 (The Pile)

Max Activating Token Index: 633

Text #10

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9216. Min Act: -0.0000

Data Index: 1622878 (The Pile)

Max Activating Token Index: 599

Text #11

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9665. Min Act: -0.0000

Data Index: 1361885 (The Pile)

Max Activating Token Index: 358

Text #12

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9027. Min Act: -0.0000

Data Index: 790022 (The Pile)

Max Activating Token Index: 438

Text #13

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9066. Min Act: -0.0000

Data Index: 1151556 (The Pile)

Max Activating Token Index: 505

Text #14

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9254. Min Act: -0.0000

Data Index: 265021 (The Pile)

Max Activating Token Index: 490

Text #15

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9257. Min Act: -0.0000

Data Index: 659326 (The Pile)

Max Activating Token Index: 80

Text #16

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8667. Min Act: -0.0000

Data Index: 1657201 (The Pile)

Max Activating Token Index: 139

Text #17

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9170. Min Act: -0.0000

Data Index: 34618 (The Pile)

Max Activating Token Index: 601

Text #18

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8608. Min Act: -0.0000

Data Index: 227467 (The Pile)

Max Activating Token Index: 179

Text #19

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8793. Min Act: -0.0000

Data Index: 737984 (The Pile)

Max Activating Token Index: 612