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

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

Neuron 4414 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.5072. Min Act: -0.0000

Data Index: 1617930 (Python Code)

Max Activating Token Index: 67

Text #1

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.3347. Min Act: -0.0000

Data Index: 1635783 (Python Code)

Max Activating Token Index: 762

Text #2

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.2079. Min Act: -0.0000

Data Index: 1370625 (Python Code)

Max Activating Token Index: 46

Text #3

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.1042. Min Act: -0.0000

Data Index: 1425585 (Python Code)

Max Activating Token Index: 51

Text #4

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.1042. Min Act: -0.0000

Data Index: 1583135 (Python Code)

Max Activating Token Index: 51

Text #5

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.0486. Min Act: -0.0000

Data Index: 1515002 (Python Code)

Max Activating Token Index: 40

Text #6

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.1243. Min Act: -0.0000

Data Index: 1526707 (Python Code)

Max Activating Token Index: 934

Text #7

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.1789. Min Act: -0.0000

Data Index: 1650557 (Python Code)

Max Activating Token Index: 999

Text #8

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.1038. Min Act: -0.0000

Data Index: 1558056 (Python Code)

Max Activating Token Index: 49

Text #9

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.0703. Min Act: -0.0001

Data Index: 1642770 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.0586. Min Act: -0.0001

Data Index: 1386787 (Python Code)

Max Activating Token Index: 47

Text #11

Max Range: 1.5072. Min Range: -1.5072

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1459275 (Python Code)

Max Activating Token Index: 362

Text #12

Max Range: 1.5072. Min Range: -1.5072

Max Act: 0.9474. Min Act: -0.0000

Data Index: 1630706 (Python Code)

Max Activating Token Index: 987

Text #13

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.0598. Min Act: -0.0000

Data Index: 1509111 (Python Code)

Max Activating Token Index: 296

Text #14

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.0654. Min Act: -0.0000

Data Index: 1651969 (Python Code)

Max Activating Token Index: 49

Text #15

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.0006. Min Act: -0.0000

Data Index: 1435101 (Python Code)

Max Activating Token Index: 954

Text #16

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.0553. Min Act: -0.0001

Data Index: 1511529 (Python Code)

Max Activating Token Index: 52

Text #17

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.0553. Min Act: -0.0001

Data Index: 1566000 (Python Code)

Max Activating Token Index: 52

Text #18

Max Range: 1.5072. Min Range: -1.5072

Max Act: 0.9514. Min Act: -0.0000

Data Index: 1426993 (Python Code)

Max Activating Token Index: 1009

Text #19

Max Range: 1.5072. Min Range: -1.5072

Max Act: 1.1357. Min Act: -0.0000

Data Index: 1388274 (Python Code)

Max Activating Token Index: 46