Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3544 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1034922 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.2105. Min Act: -0.0000

Data Index: 77340 (C4 (Web Text))

Max Activating Token Index: 939

Text #2

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.2113. Min Act: -0.0000

Data Index: 1628718 (Python Code)

Max Activating Token Index: 46

Text #3

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1960. Min Act: -0.0000

Data Index: 605449 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.2133. Min Act: -0.0000

Data Index: 905118 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.2115. Min Act: -0.0000

Data Index: 758118 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1492559 (Python Code)

Max Activating Token Index: 346

Text #7

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1945. Min Act: -0.0000

Data Index: 1529032 (Python Code)

Max Activating Token Index: 57

Text #8

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1933. Min Act: -0.0000

Data Index: 1158959 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1911. Min Act: -0.0000

Data Index: 1023861 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1898. Min Act: -0.0000

Data Index: 758838 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1829. Min Act: -0.0000

Data Index: 1096081 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1893. Min Act: -0.0000

Data Index: 74246 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1663. Min Act: -0.0000

Data Index: 1199084 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1849. Min Act: -0.0000

Data Index: 41614 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1573. Min Act: -0.0000

Data Index: 1204306 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1914. Min Act: -0.0000

Data Index: 119072 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1753. Min Act: -0.0000

Data Index: 1333790 (C4 (Web Text))

Max Activating Token Index: 276

Text #18

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1527887 (Python Code)

Max Activating Token Index: 84

Text #19

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1680. Min Act: -0.0000

Data Index: 227374 (C4 (Web Text))

Max Activating Token Index: 497