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

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

Neuron 878 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: 0.2192. Min Range: -0.2192

Max Act: 0.2192. Min Act: -0.0001

Data Index: 1577857 (Python Code)

Max Activating Token Index: 173

Text #1

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1524963 (Python Code)

Max Activating Token Index: 85

Text #2

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.2029. Min Act: -0.0000

Data Index: 1505099 (Python Code)

Max Activating Token Index: 112

Text #3

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1939. Min Act: -0.0001

Data Index: 1634986 (Python Code)

Max Activating Token Index: 29

Text #4

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1513633 (Python Code)

Max Activating Token Index: 72

Text #5

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1526613 (Python Code)

Max Activating Token Index: 161

Text #6

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1512. Min Act: -0.0001

Data Index: 1491538 (Python Code)

Max Activating Token Index: 362

Text #7

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1727. Min Act: -0.0001

Data Index: 1364385 (Python Code)

Max Activating Token Index: 185

Text #8

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1725. Min Act: -0.0001

Data Index: 1500762 (Python Code)

Max Activating Token Index: 383

Text #9

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1654441 (Python Code)

Max Activating Token Index: 25

Text #10

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1600. Min Act: -0.0000

Data Index: 1373839 (Python Code)

Max Activating Token Index: 69

Text #11

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1674. Min Act: -0.0001

Data Index: 1597890 (Python Code)

Max Activating Token Index: 181

Text #12

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1655. Min Act: -0.0001

Data Index: 1428549 (Python Code)

Max Activating Token Index: 137

Text #13

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1677. Min Act: -0.0000

Data Index: 1553118 (Python Code)

Max Activating Token Index: 22

Text #14

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1630. Min Act: -0.0001

Data Index: 1482738 (Python Code)

Max Activating Token Index: 616

Text #15

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1517. Min Act: -0.0001

Data Index: 1575022 (Python Code)

Max Activating Token Index: 106

Text #16

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1787. Min Act: -0.0001

Data Index: 1555357 (Python Code)

Max Activating Token Index: 138

Text #17

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1516. Min Act: -0.0000

Data Index: 1498480 (Python Code)

Max Activating Token Index: 102

Text #18

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1469. Min Act: -0.0001

Data Index: 1407646 (Python Code)

Max Activating Token Index: 661

Text #19

Max Range: 0.2192. Min Range: -0.2192

Max Act: 0.1552. Min Act: -0.0000

Data Index: 1496311 (Python Code)

Max Activating Token Index: 74