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

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

Neuron 132 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: 0.5072. Min Range: -0.5072

Max Act: 0.5072. Min Act: -0.0001

Data Index: 1562241 (Python Code)

Max Activating Token Index: 880

Text #1

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4907. Min Act: -0.0001

Data Index: 1561786 (Python Code)

Max Activating Token Index: 959

Text #2

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4371. Min Act: -0.0001

Data Index: 1367090 (Python Code)

Max Activating Token Index: 822

Text #3

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4566. Min Act: -0.0001

Data Index: 1591309 (Python Code)

Max Activating Token Index: 576

Text #4

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4488. Min Act: -0.0001

Data Index: 299593 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4597. Min Act: -0.0001

Data Index: 1545161 (Python Code)

Max Activating Token Index: 717

Text #6

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4341. Min Act: -0.0001

Data Index: 1137887 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4344. Min Act: -0.0001

Data Index: 1631154 (Python Code)

Max Activating Token Index: 28

Text #8

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4269. Min Act: -0.0001

Data Index: 1571239 (Python Code)

Max Activating Token Index: 34

Text #9

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3873. Min Act: -0.0001

Data Index: 1419730 (Python Code)

Max Activating Token Index: 1010

Text #10

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4227. Min Act: -0.0001

Data Index: 1166685 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3934. Min Act: -0.0001

Data Index: 607769 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3799. Min Act: -0.0001

Data Index: 265673 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3926. Min Act: -0.0001

Data Index: 1586316 (Python Code)

Max Activating Token Index: 376

Text #14

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3918. Min Act: -0.0001

Data Index: 1472676 (Python Code)

Max Activating Token Index: 801

Text #15

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3763. Min Act: -0.0001

Data Index: 1270097 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3960. Min Act: -0.0001

Data Index: 1439106 (Python Code)

Max Activating Token Index: 887

Text #17

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3958. Min Act: -0.0001

Data Index: 1409062 (Python Code)

Max Activating Token Index: 41

Text #18

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.3940. Min Act: -0.0001

Data Index: 1425548 (Python Code)

Max Activating Token Index: 107

Text #19

Max Range: 0.5072. Min Range: -0.5072

Max Act: 0.4068. Min Act: -0.0001

Data Index: 1414305 (Python Code)

Max Activating Token Index: 766