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

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

Neuron 3744 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1597. Min Act: -0.0000

Data Index: 1585744 (Python Code)

Max Activating Token Index: 165

Text #1

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1012548 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1423. Min Act: -0.0000

Data Index: 1466795 (Python Code)

Max Activating Token Index: 723

Text #3

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1259. Min Act: 0.0000

Data Index: 392351 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1237. Min Act: -0.0001

Data Index: 1405211 (Python Code)

Max Activating Token Index: 524

Text #5

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1099. Min Act: -0.0000

Data Index: 819326 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1286. Min Act: -0.0001

Data Index: 5282 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1111. Min Act: 0.0000

Data Index: 363720 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1230. Min Act: 0.0000

Data Index: 441746 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1181. Min Act: -0.0000

Data Index: 1226885 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1115. Min Act: -0.0000

Data Index: 852998 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.0985. Min Act: -0.0000

Data Index: 163526 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1052. Min Act: -0.0001

Data Index: 209884 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.0979. Min Act: -0.0000

Data Index: 1046271 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1279738 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.0902. Min Act: -0.0001

Data Index: 1542504 (Python Code)

Max Activating Token Index: 725

Text #16

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.0898. Min Act: -0.0001

Data Index: 806695 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1397294 (Python Code)

Max Activating Token Index: 1003

Text #18

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.0841. Min Act: -0.0000

Data Index: 1636029 (Python Code)

Max Activating Token Index: 686

Text #19

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.0918. Min Act: -0.0001

Data Index: 1609047 (Python Code)

Max Activating Token Index: 879