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

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

Neuron 48 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: 1.7943. Min Range: -1.7943

Max Act: 1.7843. Min Act: -0.0001

Data Index: 1418640 (Python Code)

Max Activating Token Index: 725

Text #1

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.6803. Min Act: -0.0001

Data Index: 1615674 (Python Code)

Max Activating Token Index: 642

Text #2

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.7943. Min Act: -0.0001

Data Index: 1562897 (Python Code)

Max Activating Token Index: 711

Text #3

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.6858. Min Act: -0.0001

Data Index: 1625304 (Python Code)

Max Activating Token Index: 114

Text #4

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.5693. Min Act: -0.0001

Data Index: 1433659 (Python Code)

Max Activating Token Index: 745

Text #5

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.6106. Min Act: -0.0001

Data Index: 1373255 (Python Code)

Max Activating Token Index: 759

Text #6

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.5839. Min Act: -0.0001

Data Index: 1401331 (Python Code)

Max Activating Token Index: 106

Text #7

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.6027. Min Act: -0.0001

Data Index: 1553201 (Python Code)

Max Activating Token Index: 111

Text #8

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.7145. Min Act: -0.0001

Data Index: 1403191 (Python Code)

Max Activating Token Index: 171

Text #9

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.4399. Min Act: -0.0001

Data Index: 1572862 (Python Code)

Max Activating Token Index: 776

Text #10

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.7016. Min Act: -0.0001

Data Index: 1410325 (Python Code)

Max Activating Token Index: 82

Text #11

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.5356. Min Act: -0.0001

Data Index: 1636152 (Python Code)

Max Activating Token Index: 668

Text #12

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.3119. Min Act: -0.0001

Data Index: 1632909 (Python Code)

Max Activating Token Index: 612

Text #13

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.6414. Min Act: -0.0001

Data Index: 1519732 (Python Code)

Max Activating Token Index: 56

Text #14

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.5832. Min Act: -0.0001

Data Index: 1557636 (Python Code)

Max Activating Token Index: 49

Text #15

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.5576. Min Act: -0.0001

Data Index: 1620352 (Python Code)

Max Activating Token Index: 637

Text #16

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.4780. Min Act: -0.0001

Data Index: 1401621 (Python Code)

Max Activating Token Index: 641

Text #17

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.5937. Min Act: -0.0001

Data Index: 1513926 (Python Code)

Max Activating Token Index: 225

Text #18

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.6042. Min Act: -0.0001

Data Index: 1397442 (Python Code)

Max Activating Token Index: 904

Text #19

Max Range: 1.7943. Min Range: -1.7943

Max Act: 1.5766. Min Act: -0.0001

Data Index: 1566918 (Python Code)

Max Activating Token Index: 980