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

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

Neuron 2501 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1709. Min Act: -0.0000

Data Index: 78465 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1808. Min Act: -0.0000

Data Index: 30066 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1952. Min Act: -0.0000

Data Index: 1240587 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1916. Min Act: -0.0000

Data Index: 165341 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1850. Min Act: -0.0000

Data Index: 832764 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1066295 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1753. Min Act: -0.0000

Data Index: 418535 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1555. Min Act: -0.0000

Data Index: 569035 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1605. Min Act: -0.0000

Data Index: 474292 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1531. Min Act: -0.0000

Data Index: 692367 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1621. Min Act: -0.0000

Data Index: 603687 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1728. Min Act: -0.0000

Data Index: 914043 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1550. Min Act: -0.0000

Data Index: 324198 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1691. Min Act: -0.0000

Data Index: 349792 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1538. Min Act: -0.0000

Data Index: 866749 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1446. Min Act: -0.0000

Data Index: 344992 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1435. Min Act: -0.0000

Data Index: 610422 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1465. Min Act: -0.0000

Data Index: 32773 (C4 (Web Text))

Max Activating Token Index: 932

Text #18

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1437. Min Act: -0.0000

Data Index: 1078412 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.1952. Min Range: -0.1952

Max Act: 0.1484. Min Act: -0.0000

Data Index: 258579 (C4 (Web Text))

Max Activating Token Index: 261