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

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

Neuron 434 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1391. Min Range: -2.1391

Max Act: 2.0736. Min Act: -0.0000

Data Index: 1432315 (Python Code)

Max Activating Token Index: 47

Text #1

Max Range: 2.1391. Min Range: -2.1391

Max Act: 2.0591. Min Act: -0.0000

Data Index: 1565173 (Python Code)

Max Activating Token Index: 31

Text #2

Max Range: 2.1391. Min Range: -2.1391

Max Act: 1.9124. Min Act: -0.0000

Data Index: 1485813 (Python Code)

Max Activating Token Index: 132

Text #3

Max Range: 2.1391. Min Range: -2.1391

Max Act: 2.1391. Min Act: -0.0000

Data Index: 1540258 (Python Code)

Max Activating Token Index: 27

Text #4

Max Range: 2.1391. Min Range: -2.1391

Max Act: 2.1152. Min Act: -0.0000

Data Index: 1610066 (Python Code)

Max Activating Token Index: 26

Text #5

Max Range: 2.1391. Min Range: -2.1391

Max Act: 1.9776. Min Act: -0.0000

Data Index: 1602593 (Python Code)

Max Activating Token Index: 62

Text #6

Max Range: 2.1391. Min Range: -2.1391

Max Act: 1.9776. Min Act: -0.0000

Data Index: 1614135 (Python Code)

Max Activating Token Index: 62

Text #7

Max Range: 2.1391. Min Range: -2.1391

Max Act: 1.9325. Min Act: -0.0000

Data Index: 1640050 (Python Code)

Max Activating Token Index: 28

Text #8

Max Range: 2.1391. Min Range: -2.1391

Max Act: 1.8344. Min Act: -0.0000

Data Index: 1528382 (Python Code)

Max Activating Token Index: 29

Text #9

Max Range: 2.1391. Min Range: -2.1391

Max Act: 1.8562. Min Act: -0.0000

Data Index: 1405490 (Python Code)

Max Activating Token Index: 154

Text #10

Max Range: 2.1391. Min Range: -2.1391

Max Act: 1.8611. Min Act: -0.0000

Data Index: 1447088 (Python Code)

Max Activating Token Index: 129

Text #11

Max Range: 2.1391. Min Range: -2.1391

Max Act: 1.8169. Min Act: -0.0000

Data Index: 1400676 (Python Code)

Max Activating Token Index: 50

Text #12

Max Range: 2.1391. Min Range: -2.1391

Max Act: 1.6999. Min Act: -0.0000

Data Index: 1638580 (Python Code)

Max Activating Token Index: 200

Text #13

Max Range: 2.1391. Min Range: -2.1391

Max Act: 1.8355. Min Act: -0.0000

Data Index: 1467868 (Python Code)

Max Activating Token Index: 33

Text #14

Max Range: 2.1391. Min Range: -2.1391

Max Act: 1.7895. Min Act: -0.0000

Data Index: 1489117 (Python Code)

Max Activating Token Index: 30

Text #15

Max Range: 2.1391. Min Range: -2.1391

Max Act: 1.7741. Min Act: -0.0000

Data Index: 1490488 (Python Code)

Max Activating Token Index: 61

Text #16

Max Range: 2.1391. Min Range: -2.1391

Max Act: 1.7653. Min Act: -0.0000

Data Index: 1498609 (Python Code)

Max Activating Token Index: 155

Text #17

Max Range: 2.1391. Min Range: -2.1391

Max Act: 1.7643. Min Act: -0.0000

Data Index: 1655247 (Python Code)

Max Activating Token Index: 140

Text #18

Max Range: 2.1391. Min Range: -2.1391

Max Act: 1.7648. Min Act: -0.0000

Data Index: 1450952 (Python Code)

Max Activating Token Index: 51

Text #19

Max Range: 2.1391. Min Range: -2.1391

Max Act: 1.8085. Min Act: -0.0000

Data Index: 1414595 (Python Code)

Max Activating Token Index: 143