Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3931 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0676. Min Act: -0.0001

Data Index: 1015388 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0672. Min Act: -0.0001

Data Index: 1495403 (Python Code)

Max Activating Token Index: 94

Text #2

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1517160 (Python Code)

Max Activating Token Index: 833

Text #3

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0638. Min Act: -0.0001

Data Index: 1269949 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1224401 (C4 (Web Text))

Max Activating Token Index: 55

Text #5

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0584. Min Act: -0.0001

Data Index: 1533647 (Python Code)

Max Activating Token Index: 113

Text #6

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0650. Min Act: -0.0001

Data Index: 1334489 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0629. Min Act: -0.0001

Data Index: 1469899 (Python Code)

Max Activating Token Index: 113

Text #8

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0561. Min Act: -0.0001

Data Index: 762218 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0560. Min Act: -0.0001

Data Index: 1603811 (Python Code)

Max Activating Token Index: 60

Text #10

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0600. Min Act: -0.0001

Data Index: 1481237 (Python Code)

Max Activating Token Index: 82

Text #11

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0642. Min Act: -0.0001

Data Index: 328300 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0598. Min Act: -0.0001

Data Index: 1413260 (Python Code)

Max Activating Token Index: 38

Text #13

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0587. Min Act: -0.0001

Data Index: 121857 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0587. Min Act: -0.0001

Data Index: 1415920 (Python Code)

Max Activating Token Index: 276

Text #15

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0600. Min Act: -0.0001

Data Index: 816835 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0548. Min Act: -0.0001

Data Index: 22545 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0612. Min Act: -0.0001

Data Index: 1569710 (Python Code)

Max Activating Token Index: 231

Text #18

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0566. Min Act: -0.0001

Data Index: 1434115 (Python Code)

Max Activating Token Index: 422

Text #19

Max Range: 0.0676. Min Range: -0.0676

Max Act: 0.0563. Min Act: -0.0001

Data Index: 1550706 (Python Code)

Max Activating Token Index: 702