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

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

Neuron 2717 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9424. Min Range: -2.9424

Max Act: 2.9424. Min Act: -0.0000

Data Index: 1581800 (Python Code)

Max Activating Token Index: 21

Text #1

Max Range: 2.9424. Min Range: -2.9424

Max Act: 2.3109. Min Act: -0.0000

Data Index: 1565275 (Python Code)

Max Activating Token Index: 21

Text #2

Max Range: 2.9424. Min Range: -2.9424

Max Act: 2.1738. Min Act: -0.0000

Data Index: 1514138 (Python Code)

Max Activating Token Index: 23

Text #3

Max Range: 2.9424. Min Range: -2.9424

Max Act: 2.1082. Min Act: -0.0000

Data Index: 1432258 (Python Code)

Max Activating Token Index: 44

Text #4

Max Range: 2.9424. Min Range: -2.9424

Max Act: 2.1736. Min Act: -0.0000

Data Index: 1425169 (Python Code)

Max Activating Token Index: 21

Text #5

Max Range: 2.9424. Min Range: -2.9424

Max Act: 2.0364. Min Act: -0.0000

Data Index: 1508203 (Python Code)

Max Activating Token Index: 29

Text #6

Max Range: 2.9424. Min Range: -2.9424

Max Act: 2.0279. Min Act: -0.0000

Data Index: 1615659 (Python Code)

Max Activating Token Index: 42

Text #7

Max Range: 2.9424. Min Range: -2.9424

Max Act: 1.9167. Min Act: -0.0000

Data Index: 1528569 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 2.9424. Min Range: -2.9424

Max Act: 2.0136. Min Act: -0.0000

Data Index: 1643312 (Python Code)

Max Activating Token Index: 31

Text #9

Max Range: 2.9424. Min Range: -2.9424

Max Act: 2.1293. Min Act: -0.0000

Data Index: 1411502 (Python Code)

Max Activating Token Index: 72

Text #10

Max Range: 2.9424. Min Range: -2.9424

Max Act: 2.0208. Min Act: -0.0000

Data Index: 1617125 (Python Code)

Max Activating Token Index: 47

Text #11

Max Range: 2.9424. Min Range: -2.9424

Max Act: 1.9818. Min Act: -0.0000

Data Index: 1389731 (Python Code)

Max Activating Token Index: 113

Text #12

Max Range: 2.9424. Min Range: -2.9424

Max Act: 1.9797. Min Act: -0.0000

Data Index: 1528886 (Python Code)

Max Activating Token Index: 25

Text #13

Max Range: 2.9424. Min Range: -2.9424

Max Act: 1.9848. Min Act: -0.0000

Data Index: 1568088 (Python Code)

Max Activating Token Index: 67

Text #14

Max Range: 2.9424. Min Range: -2.9424

Max Act: 1.9738. Min Act: -0.0000

Data Index: 1427106 (Python Code)

Max Activating Token Index: 71

Text #15

Max Range: 2.9424. Min Range: -2.9424

Max Act: 2.0624. Min Act: -0.0000

Data Index: 1538710 (Python Code)

Max Activating Token Index: 28

Text #16

Max Range: 2.9424. Min Range: -2.9424

Max Act: 1.9533. Min Act: -0.0000

Data Index: 1436413 (Python Code)

Max Activating Token Index: 19

Text #17

Max Range: 2.9424. Min Range: -2.9424

Max Act: 1.9469. Min Act: -0.0000

Data Index: 1375039 (Python Code)

Max Activating Token Index: 26

Text #18

Max Range: 2.9424. Min Range: -2.9424

Max Act: 1.9121. Min Act: -0.0000

Data Index: 1632732 (Python Code)

Max Activating Token Index: 39

Text #19

Max Range: 2.9424. Min Range: -2.9424

Max Act: 1.9261. Min Act: -0.0000

Data Index: 1400237 (Python Code)

Max Activating Token Index: 36