Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1341 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0768. Min Act: -0.0003

Data Index: 1464625 (Python Code)

Max Activating Token Index: 418

Text #1

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0779. Min Act: -0.0003

Data Index: 1595179 (Python Code)

Max Activating Token Index: 519

Text #2

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0739. Min Act: -0.0003

Data Index: 427106 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0674. Min Act: -0.0003

Data Index: 26614 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0633. Min Act: -0.0003

Data Index: 1652039 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0606. Min Act: -0.0003

Data Index: 775730 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0608. Min Act: -0.0003

Data Index: 1229828 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0574. Min Act: -0.0003

Data Index: 204749 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0558. Min Act: -0.0003

Data Index: 1049445 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0565. Min Act: -0.0003

Data Index: 1210147 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0566. Min Act: -0.0004

Data Index: 388772 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0543. Min Act: -0.0003

Data Index: 361072 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0563. Min Act: -0.0003

Data Index: 126387 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0544. Min Act: -0.0003

Data Index: 549923 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0544. Min Act: -0.0003

Data Index: 559690 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0545. Min Act: -0.0003

Data Index: 1164390 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0538. Min Act: -0.0003

Data Index: 363495 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0559. Min Act: -0.0003

Data Index: 162511 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0527. Min Act: -0.0003

Data Index: 223344 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0520. Min Act: -0.0003

Data Index: 1415220 (Python Code)

Max Activating Token Index: 905