Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 953 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1889. Min Act: -0.0002

Data Index: 283937 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1915. Min Act: -0.0002

Data Index: 412537 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1883. Min Act: -0.0002

Data Index: 298922 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1775. Min Act: -0.0002

Data Index: 1095946 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1736. Min Act: -0.0002

Data Index: 539612 (C4 (Web Text))

Max Activating Token Index: 532

Text #5

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1823. Min Act: -0.0002

Data Index: 255706 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1691. Min Act: -0.0002

Data Index: 1278955 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1641. Min Act: -0.0002

Data Index: 886534 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1691. Min Act: -0.0002

Data Index: 1007338 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1625. Min Act: -0.0002

Data Index: 1139351 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1730. Min Act: -0.0002

Data Index: 1017599 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1605. Min Act: -0.0002

Data Index: 841752 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1605. Min Act: -0.0002

Data Index: 392748 (C4 (Web Text))

Max Activating Token Index: 604

Text #13

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1481. Min Act: -0.0002

Data Index: 254318 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1513. Min Act: -0.0002

Data Index: 801439 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1532. Min Act: -0.0002

Data Index: 1235155 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1499. Min Act: -0.0002

Data Index: 1310783 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1498. Min Act: -0.0002

Data Index: 305205 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1463. Min Act: -0.0002

Data Index: 507948 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.1915. Min Range: -0.1915

Max Act: 0.1443. Min Act: -0.0002

Data Index: 797843 (C4 (Web Text))

Max Activating Token Index: 735