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

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

Neuron 2557 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.2180. Min Act: -0.0001

Data Index: 49888 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1963. Min Act: -0.0001

Data Index: 575051 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1989. Min Act: -0.0001

Data Index: 185895 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1918. Min Act: -0.0001

Data Index: 131422 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1651. Min Act: -0.0001

Data Index: 969160 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1679. Min Act: -0.0001

Data Index: 1154062 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1864. Min Act: -0.0001

Data Index: 937330 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1688. Min Act: -0.0001

Data Index: 1171544 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1608. Min Act: -0.0001

Data Index: 717386 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1619. Min Act: -0.0001

Data Index: 542399 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1633. Min Act: -0.0001

Data Index: 649967 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1533. Min Act: -0.0001

Data Index: 961922 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1573. Min Act: -0.0001

Data Index: 640709 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1579. Min Act: -0.0001

Data Index: 1333818 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1728. Min Act: -0.0001

Data Index: 1023641 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1466. Min Act: -0.0001

Data Index: 925479 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1433. Min Act: -0.0001

Data Index: 1065207 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1477. Min Act: -0.0001

Data Index: 796617 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1429. Min Act: -0.0001

Data Index: 1076147 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.2180. Min Range: -0.2180

Max Act: 0.1409. Min Act: -0.0001

Data Index: 66823 (C4 (Web Text))

Max Activating Token Index: 867