Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3925 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.5440. Min Act: -0.0001

Data Index: 1602791 (Python Code)

Max Activating Token Index: 77

Text #1

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.5254. Min Act: -0.0001

Data Index: 1575371 (Python Code)

Max Activating Token Index: 35

Text #2

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.5405. Min Act: -0.0001

Data Index: 1635700 (Python Code)

Max Activating Token Index: 77

Text #3

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.5115. Min Act: -0.0001

Data Index: 1435869 (Python Code)

Max Activating Token Index: 56

Text #4

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4594. Min Act: -0.0002

Data Index: 1367931 (Python Code)

Max Activating Token Index: 104

Text #5

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.5120. Min Act: -0.0001

Data Index: 1623929 (Python Code)

Max Activating Token Index: 26

Text #6

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4979. Min Act: -0.0001

Data Index: 1369534 (Python Code)

Max Activating Token Index: 64

Text #7

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.5069. Min Act: -0.0001

Data Index: 1433914 (Python Code)

Max Activating Token Index: 116

Text #8

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.5201. Min Act: -0.0002

Data Index: 1388890 (Python Code)

Max Activating Token Index: 62

Text #9

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4993. Min Act: -0.0001

Data Index: 1644007 (Python Code)

Max Activating Token Index: 119

Text #10

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4885. Min Act: -0.0001

Data Index: 1607684 (Python Code)

Max Activating Token Index: 30

Text #11

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4827. Min Act: -0.0001

Data Index: 1523948 (Python Code)

Max Activating Token Index: 183

Text #12

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4669. Min Act: -0.0001

Data Index: 1385793 (Python Code)

Max Activating Token Index: 109

Text #13

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4978. Min Act: -0.0001

Data Index: 1385266 (Python Code)

Max Activating Token Index: 456

Text #14

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4533. Min Act: -0.0001

Data Index: 1410531 (Python Code)

Max Activating Token Index: 98

Text #15

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4688. Min Act: -0.0001

Data Index: 1598054 (Python Code)

Max Activating Token Index: 97

Text #16

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4488. Min Act: -0.0001

Data Index: 1459227 (Python Code)

Max Activating Token Index: 59

Text #17

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4472. Min Act: -0.0001

Data Index: 1596373 (Python Code)

Max Activating Token Index: 356

Text #18

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4064. Min Act: -0.0001

Data Index: 1485783 (Python Code)

Max Activating Token Index: 152

Text #19

Max Range: 0.5440. Min Range: -0.5440

Max Act: 0.4017. Min Act: -0.0001

Data Index: 1378863 (Python Code)

Max Activating Token Index: 313