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

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

Neuron 624 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1184. Min Range: -6.1184

Max Act: 5.9549. Min Act: -0.0000

Data Index: 1557216 (Python Code)

Max Activating Token Index: 792

Text #1

Max Range: 6.1184. Min Range: -6.1184

Max Act: 5.2877. Min Act: -0.0000

Data Index: 1608774 (Python Code)

Max Activating Token Index: 956

Text #2

Max Range: 6.1184. Min Range: -6.1184

Max Act: 6.1184. Min Act: -0.0000

Data Index: 1618344 (Python Code)

Max Activating Token Index: 891

Text #3

Max Range: 6.1184. Min Range: -6.1184

Max Act: 5.6379. Min Act: -0.0000

Data Index: 1565150 (Python Code)

Max Activating Token Index: 790

Text #4

Max Range: 6.1184. Min Range: -6.1184

Max Act: 5.4942. Min Act: -0.0000

Data Index: 1392977 (Python Code)

Max Activating Token Index: 821

Text #5

Max Range: 6.1184. Min Range: -6.1184

Max Act: 5.4806. Min Act: -0.0000

Data Index: 1412010 (Python Code)

Max Activating Token Index: 881

Text #6

Max Range: 6.1184. Min Range: -6.1184

Max Act: 5.9890. Min Act: -0.0000

Data Index: 1482914 (Python Code)

Max Activating Token Index: 945

Text #7

Max Range: 6.1184. Min Range: -6.1184

Max Act: 5.5977. Min Act: -0.0000

Data Index: 1653299 (Python Code)

Max Activating Token Index: 872

Text #8

Max Range: 6.1184. Min Range: -6.1184

Max Act: 5.6671. Min Act: -0.0000

Data Index: 1454592 (Python Code)

Max Activating Token Index: 574

Text #9

Max Range: 6.1184. Min Range: -6.1184

Max Act: 6.0113. Min Act: -0.0000

Data Index: 1535744 (Python Code)

Max Activating Token Index: 650

Text #10

Max Range: 6.1184. Min Range: -6.1184

Max Act: 5.4436. Min Act: -0.0000

Data Index: 1569326 (Python Code)

Max Activating Token Index: 951

Text #11

Max Range: 6.1184. Min Range: -6.1184

Max Act: 5.4438. Min Act: -0.0000

Data Index: 1509981 (Python Code)

Max Activating Token Index: 951

Text #12

Max Range: 6.1184. Min Range: -6.1184

Max Act: 5.9313. Min Act: -0.0000

Data Index: 1499667 (Python Code)

Max Activating Token Index: 987

Text #13

Max Range: 6.1184. Min Range: -6.1184

Max Act: 5.1703. Min Act: -0.0000

Data Index: 1404513 (Python Code)

Max Activating Token Index: 881

Text #14

Max Range: 6.1184. Min Range: -6.1184

Max Act: 5.6745. Min Act: -0.0000

Data Index: 1475412 (Python Code)

Max Activating Token Index: 600

Text #15

Max Range: 6.1184. Min Range: -6.1184

Max Act: 5.2981. Min Act: -0.0000

Data Index: 1486918 (Python Code)

Max Activating Token Index: 716

Text #16

Max Range: 6.1184. Min Range: -6.1184

Max Act: 4.9687. Min Act: -0.0000

Data Index: 1399066 (Python Code)

Max Activating Token Index: 658

Text #17

Max Range: 6.1184. Min Range: -6.1184

Max Act: 5.3259. Min Act: -0.0000

Data Index: 1479088 (Python Code)

Max Activating Token Index: 924

Text #18

Max Range: 6.1184. Min Range: -6.1184

Max Act: 5.4511. Min Act: -0.0000

Data Index: 1643752 (Python Code)

Max Activating Token Index: 880

Text #19

Max Range: 6.1184. Min Range: -6.1184

Max Act: 5.6706. Min Act: -0.0000

Data Index: 1636764 (Python Code)

Max Activating Token Index: 648