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

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

Neuron 4929 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: 1.1525. Min Range: -1.1525

Max Act: 1.0786. Min Act: -0.0001

Data Index: 1394731 (Python Code)

Max Activating Token Index: 701

Text #1

Max Range: 1.1525. Min Range: -1.1525

Max Act: 1.1525. Min Act: -0.0001

Data Index: 1409428 (Python Code)

Max Activating Token Index: 119

Text #2

Max Range: 1.1525. Min Range: -1.1525

Max Act: 1.1052. Min Act: -0.0001

Data Index: 1410598 (Python Code)

Max Activating Token Index: 193

Text #3

Max Range: 1.1525. Min Range: -1.1525

Max Act: 1.0057. Min Act: -0.0001

Data Index: 1633161 (Python Code)

Max Activating Token Index: 803

Text #4

Max Range: 1.1525. Min Range: -1.1525

Max Act: 0.9841. Min Act: -0.0001

Data Index: 1496235 (Python Code)

Max Activating Token Index: 836

Text #5

Max Range: 1.1525. Min Range: -1.1525

Max Act: 1.0591. Min Act: -0.0000

Data Index: 1619969 (Python Code)

Max Activating Token Index: 657

Text #6

Max Range: 1.1525. Min Range: -1.1525

Max Act: 0.9936. Min Act: -0.0001

Data Index: 1498114 (Python Code)

Max Activating Token Index: 873

Text #7

Max Range: 1.1525. Min Range: -1.1525

Max Act: 1.0075. Min Act: -0.0000

Data Index: 1474697 (Python Code)

Max Activating Token Index: 617

Text #8

Max Range: 1.1525. Min Range: -1.1525

Max Act: 1.0359. Min Act: -0.0001

Data Index: 1481806 (Python Code)

Max Activating Token Index: 46

Text #9

Max Range: 1.1525. Min Range: -1.1525

Max Act: 1.0784. Min Act: -0.0001

Data Index: 1640267 (Python Code)

Max Activating Token Index: 764

Text #10

Max Range: 1.1525. Min Range: -1.1525

Max Act: 0.9618. Min Act: -0.0000

Data Index: 1440432 (Python Code)

Max Activating Token Index: 920

Text #11

Max Range: 1.1525. Min Range: -1.1525

Max Act: 1.0044. Min Act: -0.0001

Data Index: 1375491 (Python Code)

Max Activating Token Index: 206

Text #12

Max Range: 1.1525. Min Range: -1.1525

Max Act: 0.9732. Min Act: -0.0001

Data Index: 1562255 (Python Code)

Max Activating Token Index: 745

Text #13

Max Range: 1.1525. Min Range: -1.1525

Max Act: 1.0216. Min Act: -0.0001

Data Index: 1582962 (Python Code)

Max Activating Token Index: 124

Text #14

Max Range: 1.1525. Min Range: -1.1525

Max Act: 1.0097. Min Act: -0.0000

Data Index: 1595723 (Python Code)

Max Activating Token Index: 500

Text #15

Max Range: 1.1525. Min Range: -1.1525

Max Act: 0.9596. Min Act: -0.0001

Data Index: 1539449 (Python Code)

Max Activating Token Index: 725

Text #16

Max Range: 1.1525. Min Range: -1.1525

Max Act: 0.9542. Min Act: -0.0001

Data Index: 1510368 (Python Code)

Max Activating Token Index: 15

Text #17

Max Range: 1.1525. Min Range: -1.1525

Max Act: 1.0467. Min Act: -0.0001

Data Index: 1565949 (Python Code)

Max Activating Token Index: 444

Text #18

Max Range: 1.1525. Min Range: -1.1525

Max Act: 0.9784. Min Act: -0.0001

Data Index: 1364945 (Python Code)

Max Activating Token Index: 612

Text #19

Max Range: 1.1525. Min Range: -1.1525

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1633986 (Python Code)

Max Activating Token Index: 717