Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2809 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1769. Min Act: -0.0002

Data Index: 827356 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1744. Min Act: -0.0001

Data Index: 602000 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1554. Min Act: -0.0001

Data Index: 1209192 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1728. Min Act: -0.0002

Data Index: 1327911 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1669. Min Act: -0.0002

Data Index: 610482 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1637. Min Act: -0.0001

Data Index: 1305376 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1470. Min Act: -0.0001

Data Index: 895596 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1612. Min Act: -0.0002

Data Index: 16738 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1598. Min Act: -0.0002

Data Index: 909661 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1487. Min Act: -0.0001

Data Index: 1077445 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1557. Min Act: -0.0002

Data Index: 564577 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1518. Min Act: -0.0001

Data Index: 863839 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1558. Min Act: -0.0002

Data Index: 525250 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1441. Min Act: -0.0002

Data Index: 1141520 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1487. Min Act: -0.0002

Data Index: 1299686 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1339. Min Act: -0.0001

Data Index: 503509 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1488. Min Act: -0.0001

Data Index: 652309 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1590. Min Act: -0.0002

Data Index: 697960 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1434. Min Act: -0.0002

Data Index: 871330 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 0.1769. Min Range: -0.1769

Max Act: 0.1590. Min Act: -0.0002

Data Index: 895163 (C4 (Web Text))

Max Activating Token Index: 667