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

Dataset: The Pile

Neuron 3720 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: 0.8648. Min Range: -0.8648

Max Act: 0.8648. Min Act: -0.0000

Data Index: 632746 (The Pile)

Max Activating Token Index: 735

Text #1

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7918. Min Act: -0.0000

Data Index: 329788 (The Pile)

Max Activating Token Index: 275

Text #2

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.8130. Min Act: -0.0000

Data Index: 1017116 (The Pile)

Max Activating Token Index: 159

Text #3

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7590. Min Act: -0.0000

Data Index: 600502 (The Pile)

Max Activating Token Index: 977

Text #4

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.8154. Min Act: -0.0000

Data Index: 814695 (The Pile)

Max Activating Token Index: 486

Text #5

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.8048. Min Act: -0.0000

Data Index: 584896 (The Pile)

Max Activating Token Index: 751

Text #6

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7599. Min Act: -0.0000

Data Index: 1744583 (The Pile)

Max Activating Token Index: 923

Text #7

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.8250. Min Act: -0.0000

Data Index: 353995 (The Pile)

Max Activating Token Index: 824

Text #8

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7424. Min Act: -0.0000

Data Index: 337235 (The Pile)

Max Activating Token Index: 277

Text #9

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.8065. Min Act: -0.0000

Data Index: 504910 (The Pile)

Max Activating Token Index: 557

Text #10

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7682. Min Act: -0.0000

Data Index: 177933 (The Pile)

Max Activating Token Index: 96

Text #11

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7444. Min Act: -0.0000

Data Index: 1073680 (The Pile)

Max Activating Token Index: 484

Text #12

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7812. Min Act: -0.0000

Data Index: 580272 (The Pile)

Max Activating Token Index: 495

Text #13

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7697. Min Act: -0.0000

Data Index: 239423 (The Pile)

Max Activating Token Index: 490

Text #14

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7477. Min Act: -0.0000

Data Index: 1867967 (The Pile)

Max Activating Token Index: 323

Text #15

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7240. Min Act: -0.0000

Data Index: 290507 (The Pile)

Max Activating Token Index: 330

Text #16

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7375. Min Act: -0.0000

Data Index: 163598 (The Pile)

Max Activating Token Index: 337

Text #17

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.8010. Min Act: -0.0000

Data Index: 1685618 (The Pile)

Max Activating Token Index: 574

Text #18

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7269. Min Act: -0.0000

Data Index: 1789429 (The Pile)

Max Activating Token Index: 520

Text #19

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7937. Min Act: -0.0000

Data Index: 803599 (The Pile)

Max Activating Token Index: 618