Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1526 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.2211. Min Act: -0.0000

Data Index: 201615 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1841. Min Act: -0.0000

Data Index: 239368 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1816. Min Act: -0.0000

Data Index: 578864 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1761. Min Act: -0.0000

Data Index: 1052963 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1594. Min Act: -0.0000

Data Index: 1354048 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1647. Min Act: -0.0000

Data Index: 1409293 (Python Code)

Max Activating Token Index: 1008

Text #6

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1606. Min Act: -0.0000

Data Index: 816826 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1662. Min Act: -0.0000

Data Index: 13126 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1538. Min Act: -0.0000

Data Index: 1066790 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1713. Min Act: -0.0000

Data Index: 801530 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1591. Min Act: -0.0000

Data Index: 453715 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1397. Min Act: -0.0000

Data Index: 585915 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1283. Min Act: -0.0000

Data Index: 1582663 (Python Code)

Max Activating Token Index: 1006

Text #13

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1423. Min Act: -0.0000

Data Index: 1445419 (Python Code)

Max Activating Token Index: 666

Text #14

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1441533 (Python Code)

Max Activating Token Index: 764

Text #15

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1354. Min Act: -0.0000

Data Index: 1344371 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1322. Min Act: -0.0000

Data Index: 1488391 (Python Code)

Max Activating Token Index: 789

Text #17

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1527. Min Act: -0.0000

Data Index: 311402 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1404. Min Act: -0.0000

Data Index: 740618 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.2211. Min Range: -0.2211

Max Act: 0.1392. Min Act: -0.0000

Data Index: 1617934 (Python Code)

Max Activating Token Index: 1009