Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4144 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.2645. Min Range: -7.2645

Max Act: 7.2645. Min Act: -0.0000

Data Index: 1620777 (Python Code)

Max Activating Token Index: 941

Text #1

Max Range: 7.2645. Min Range: -7.2645

Max Act: 6.8820. Min Act: -0.0000

Data Index: 1621890 (Python Code)

Max Activating Token Index: 771

Text #2

Max Range: 7.2645. Min Range: -7.2645

Max Act: 6.1067. Min Act: -0.0000

Data Index: 1588790 (Python Code)

Max Activating Token Index: 702

Text #3

Max Range: 7.2645. Min Range: -7.2645

Max Act: 5.4452. Min Act: -0.0000

Data Index: 1518327 (Python Code)

Max Activating Token Index: 399

Text #4

Max Range: 7.2645. Min Range: -7.2645

Max Act: 5.2989. Min Act: -0.0000

Data Index: 1377579 (Python Code)

Max Activating Token Index: 897

Text #5

Max Range: 7.2645. Min Range: -7.2645

Max Act: 5.4193. Min Act: -0.0000

Data Index: 1566120 (Python Code)

Max Activating Token Index: 520

Text #6

Max Range: 7.2645. Min Range: -7.2645

Max Act: 5.3463. Min Act: -0.0000

Data Index: 1369813 (Python Code)

Max Activating Token Index: 904

Text #7

Max Range: 7.2645. Min Range: -7.2645

Max Act: 5.0670. Min Act: -0.0000

Data Index: 1560258 (Python Code)

Max Activating Token Index: 25

Text #8

Max Range: 7.2645. Min Range: -7.2645

Max Act: 5.2335. Min Act: -0.0000

Data Index: 1589743 (Python Code)

Max Activating Token Index: 71

Text #9

Max Range: 7.2645. Min Range: -7.2645

Max Act: 5.2271. Min Act: -0.0000

Data Index: 1592071 (Python Code)

Max Activating Token Index: 737

Text #10

Max Range: 7.2645. Min Range: -7.2645

Max Act: 5.3663. Min Act: -0.0000

Data Index: 1368406 (Python Code)

Max Activating Token Index: 977

Text #11

Max Range: 7.2645. Min Range: -7.2645

Max Act: 5.1029. Min Act: -0.0000

Data Index: 1534324 (Python Code)

Max Activating Token Index: 176

Text #12

Max Range: 7.2645. Min Range: -7.2645

Max Act: 5.0243. Min Act: -0.0000

Data Index: 1630434 (Python Code)

Max Activating Token Index: 869

Text #13

Max Range: 7.2645. Min Range: -7.2645

Max Act: 4.9966. Min Act: -0.0000

Data Index: 1384644 (Python Code)

Max Activating Token Index: 182

Text #14

Max Range: 7.2645. Min Range: -7.2645

Max Act: 4.9870. Min Act: -0.0000

Data Index: 1373340 (Python Code)

Max Activating Token Index: 593

Text #15

Max Range: 7.2645. Min Range: -7.2645

Max Act: 5.1477. Min Act: -0.0000

Data Index: 1532573 (Python Code)

Max Activating Token Index: 980

Text #16

Max Range: 7.2645. Min Range: -7.2645

Max Act: 4.7458. Min Act: -0.0000

Data Index: 1569164 (Python Code)

Max Activating Token Index: 862

Text #17

Max Range: 7.2645. Min Range: -7.2645

Max Act: 5.2470. Min Act: -0.0000

Data Index: 1574698 (Python Code)

Max Activating Token Index: 999

Text #18

Max Range: 7.2645. Min Range: -7.2645

Max Act: 4.7444. Min Act: -0.0000

Data Index: 1447445 (Python Code)

Max Activating Token Index: 283

Text #19

Max Range: 7.2645. Min Range: -7.2645

Max Act: 4.5606. Min Act: -0.0000

Data Index: 1616059 (Python Code)

Max Activating Token Index: 955