Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1600 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1890. Min Act: -0.0001

Data Index: 525574 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1851. Min Act: -0.0001

Data Index: 333503 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1667. Min Act: -0.0001

Data Index: 1195627 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1591. Min Act: -0.0001

Data Index: 241205 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1685. Min Act: -0.0001

Data Index: 516704 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1416. Min Act: -0.0001

Data Index: 792170 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1532. Min Act: -0.0001

Data Index: 732144 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1530. Min Act: -0.0001

Data Index: 942428 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1556. Min Act: -0.0001

Data Index: 214721 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1447. Min Act: -0.0001

Data Index: 889523 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1475. Min Act: -0.0001

Data Index: 331779 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1398. Min Act: -0.0001

Data Index: 715797 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1377. Min Act: -0.0001

Data Index: 1011334 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1375. Min Act: -0.0001

Data Index: 840363 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1420. Min Act: -0.0001

Data Index: 95670 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1467. Min Act: -0.0001

Data Index: 1344768 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1413. Min Act: -0.0001

Data Index: 1146310 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1411. Min Act: -0.0001

Data Index: 1140314 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1436. Min Act: -0.0001

Data Index: 1192407 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1388. Min Act: -0.0001

Data Index: 1226343 (C4 (Web Text))

Max Activating Token Index: 501