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

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

Neuron 1536 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1620984 (Python Code)

Max Activating Token Index: 347

Text #1

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2778. Min Act: -0.0000

Data Index: 860206 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2308. Min Act: -0.0000

Data Index: 1334647 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2021. Min Act: -0.0000

Data Index: 472867 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1285699 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.1853. Min Act: -0.0000

Data Index: 438330 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.1769. Min Act: -0.0000

Data Index: 1566508 (Python Code)

Max Activating Token Index: 237

Text #7

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.1497. Min Act: -0.0000

Data Index: 1614400 (Python Code)

Max Activating Token Index: 759

Text #8

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1517497 (Python Code)

Max Activating Token Index: 164

Text #9

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.1664. Min Act: -0.0000

Data Index: 288527 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.1609. Min Act: -0.0000

Data Index: 471447 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.1705. Min Act: -0.0001

Data Index: 1466670 (Python Code)

Max Activating Token Index: 351

Text #12

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.1705. Min Act: -0.0000

Data Index: 1594609 (Python Code)

Max Activating Token Index: 849

Text #13

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.1796. Min Act: -0.0000

Data Index: 271470 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.1660. Min Act: -0.0000

Data Index: 335045 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.1517. Min Act: -0.0000

Data Index: 1079296 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.1607. Min Act: -0.0000

Data Index: 983446 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.1533. Min Act: -0.0000

Data Index: 421758 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.1361. Min Act: -0.0000

Data Index: 1442322 (Python Code)

Max Activating Token Index: 853

Text #19

Max Range: 0.2778. Min Range: -0.2778

Max Act: 0.1443. Min Act: -0.0000

Data Index: 1472674 (Python Code)

Max Activating Token Index: 581