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

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

Neuron 2209 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1950. Min Act: -0.0000

Data Index: 146563 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1950. Min Act: -0.0000

Data Index: 171519 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1723. Min Act: -0.0000

Data Index: 427557 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1685. Min Act: -0.0000

Data Index: 1292992 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1715. Min Act: -0.0000

Data Index: 111825 (C4 (Web Text))

Max Activating Token Index: 94

Text #5

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1528. Min Act: -0.0000

Data Index: 669890 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1683. Min Act: -0.0000

Data Index: 1038204 (C4 (Web Text))

Max Activating Token Index: 376

Text #7

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1653. Min Act: -0.0000

Data Index: 751571 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1586. Min Act: -0.0000

Data Index: 1043729 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1526. Min Act: -0.0000

Data Index: 121950 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1567. Min Act: -0.0000

Data Index: 309643 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1439. Min Act: -0.0000

Data Index: 781155 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1446. Min Act: -0.0000

Data Index: 417883 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1483. Min Act: -0.0000

Data Index: 943044 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1454. Min Act: -0.0000

Data Index: 166381 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1432. Min Act: -0.0000

Data Index: 594928 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1412. Min Act: -0.0000

Data Index: 1018050 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1361. Min Act: -0.0000

Data Index: 1294347 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1358. Min Act: -0.0000

Data Index: 1335757 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.1950. Min Range: -0.1950

Max Act: 0.1251. Min Act: -0.0000

Data Index: 1156398 (C4 (Web Text))

Max Activating Token Index: 46