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

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

Neuron 4151 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: 1.0673. Min Range: -1.0673

Max Act: 1.0673. Min Act: -0.0000

Data Index: 1591878 (Python Code)

Max Activating Token Index: 43

Text #1

Max Range: 1.0673. Min Range: -1.0673

Max Act: 1.0609. Min Act: -0.0000

Data Index: 1399443 (Python Code)

Max Activating Token Index: 708

Text #2

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.9403. Min Act: -0.0000

Data Index: 1431071 (Python Code)

Max Activating Token Index: 35

Text #3

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.9752. Min Act: -0.0000

Data Index: 1634540 (Python Code)

Max Activating Token Index: 92

Text #4

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.8855. Min Act: -0.0000

Data Index: 1530310 (Python Code)

Max Activating Token Index: 519

Text #5

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1587940 (Python Code)

Max Activating Token Index: 466

Text #6

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.8632. Min Act: -0.0000

Data Index: 1391886 (Python Code)

Max Activating Token Index: 937

Text #7

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.7827. Min Act: -0.0000

Data Index: 1412857 (Python Code)

Max Activating Token Index: 25

Text #8

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1630331 (Python Code)

Max Activating Token Index: 847

Text #9

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.7851. Min Act: -0.0000

Data Index: 1507751 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.7867. Min Act: -0.0000

Data Index: 1626667 (Python Code)

Max Activating Token Index: 47

Text #11

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.7599. Min Act: -0.0000

Data Index: 1440626 (Python Code)

Max Activating Token Index: 355

Text #12

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1401834 (Python Code)

Max Activating Token Index: 61

Text #13

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.7365. Min Act: -0.0000

Data Index: 1462707 (Python Code)

Max Activating Token Index: 337

Text #14

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.7287. Min Act: -0.0000

Data Index: 1535280 (Python Code)

Max Activating Token Index: 430

Text #15

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.7496. Min Act: -0.0000

Data Index: 1387426 (Python Code)

Max Activating Token Index: 116

Text #16

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1368465 (Python Code)

Max Activating Token Index: 205

Text #17

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.7029. Min Act: -0.0000

Data Index: 1402276 (Python Code)

Max Activating Token Index: 944

Text #18

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.6919. Min Act: -0.0000

Data Index: 1653798 (Python Code)

Max Activating Token Index: 18

Text #19

Max Range: 1.0673. Min Range: -1.0673

Max Act: 0.6930. Min Act: -0.0000

Data Index: 1465032 (Python Code)

Max Activating Token Index: 13