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

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

Neuron 438 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1946. Min Act: -0.0005

Data Index: 260510 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1829. Min Act: -0.0005

Data Index: 1256625 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1640. Min Act: -0.0005

Data Index: 885710 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1663. Min Act: -0.0005

Data Index: 1246897 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1640. Min Act: -0.0005

Data Index: 31029 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1653. Min Act: -0.0005

Data Index: 1211472 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1523. Min Act: -0.0005

Data Index: 1233524 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1636. Min Act: -0.0005

Data Index: 352905 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1565. Min Act: -0.0005

Data Index: 248867 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1738. Min Act: -0.0005

Data Index: 1219052 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1531. Min Act: -0.0005

Data Index: 46449 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1405. Min Act: -0.0005

Data Index: 593072 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1517. Min Act: -0.0005

Data Index: 655116 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1405. Min Act: -0.0005

Data Index: 139146 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1498. Min Act: -0.0005

Data Index: 22854 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1556. Min Act: -0.0005

Data Index: 176838 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1492. Min Act: -0.0005

Data Index: 1316197 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1406. Min Act: -0.0005

Data Index: 511809 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1296. Min Act: -0.0005

Data Index: 271971 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1410. Min Act: -0.0005

Data Index: 560775 (C4 (Web Text))

Max Activating Token Index: 355