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

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

Neuron 3428 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.2399. Min Act: -0.0000

Data Index: 1573386 (Python Code)

Max Activating Token Index: 141

Text #1

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.1265. Min Act: -0.0000

Data Index: 1516295 (Python Code)

Max Activating Token Index: 152

Text #2

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.1207. Min Act: -0.0000

Data Index: 1419067 (Python Code)

Max Activating Token Index: 32

Text #3

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0716. Min Act: -0.0000

Data Index: 1483694 (Python Code)

Max Activating Token Index: 123

Text #4

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0608. Min Act: -0.0000

Data Index: 1543946 (Python Code)

Max Activating Token Index: 123

Text #5

Max Range: 1.2399. Min Range: -1.2399

Max Act: 0.9916. Min Act: -0.0000

Data Index: 1537898 (Python Code)

Max Activating Token Index: 87

Text #6

Max Range: 1.2399. Min Range: -1.2399

Max Act: 0.9888. Min Act: -0.0000

Data Index: 1610980 (Python Code)

Max Activating Token Index: 28

Text #7

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0421. Min Act: -0.0000

Data Index: 1374741 (Python Code)

Max Activating Token Index: 29

Text #8

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0149. Min Act: -0.0000

Data Index: 1549516 (Python Code)

Max Activating Token Index: 50

Text #9

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0141. Min Act: -0.0000

Data Index: 1466069 (Python Code)

Max Activating Token Index: 88

Text #10

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0121. Min Act: -0.0000

Data Index: 1369575 (Python Code)

Max Activating Token Index: 56

Text #11

Max Range: 1.2399. Min Range: -1.2399

Max Act: 0.9924. Min Act: -0.0000

Data Index: 1603214 (Python Code)

Max Activating Token Index: 160

Text #12

Max Range: 1.2399. Min Range: -1.2399

Max Act: 0.9780. Min Act: -0.0000

Data Index: 1408233 (Python Code)

Max Activating Token Index: 25

Text #13

Max Range: 1.2399. Min Range: -1.2399

Max Act: 0.9779. Min Act: -0.0000

Data Index: 1491474 (Python Code)

Max Activating Token Index: 25

Text #14

Max Range: 1.2399. Min Range: -1.2399

Max Act: 0.9749. Min Act: -0.0000

Data Index: 1579618 (Python Code)

Max Activating Token Index: 26

Text #15

Max Range: 1.2399. Min Range: -1.2399

Max Act: 0.9107. Min Act: -0.0000

Data Index: 1542920 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 1.2399. Min Range: -1.2399

Max Act: 0.9625. Min Act: -0.0000

Data Index: 1430454 (Python Code)

Max Activating Token Index: 110

Text #17

Max Range: 1.2399. Min Range: -1.2399

Max Act: 0.9717. Min Act: -0.0000

Data Index: 1654462 (Python Code)

Max Activating Token Index: 162

Text #18

Max Range: 1.2399. Min Range: -1.2399

Max Act: 0.9679. Min Act: -0.0000

Data Index: 1450149 (Python Code)

Max Activating Token Index: 75

Text #19

Max Range: 1.2399. Min Range: -1.2399

Max Act: 0.9649. Min Act: -0.0000

Data Index: 1599451 (Python Code)

Max Activating Token Index: 29