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

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

Neuron 3024 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.3261. Min Act: -0.0000

Data Index: 1539285 (Python Code)

Max Activating Token Index: 76

Text #1

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2990. Min Act: -0.0000

Data Index: 1641829 (Python Code)

Max Activating Token Index: 46

Text #2

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1432333 (Python Code)

Max Activating Token Index: 888

Text #3

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1194629 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1481204 (Python Code)

Max Activating Token Index: 603

Text #5

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1592855 (Python Code)

Max Activating Token Index: 556

Text #6

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.2035. Min Act: -0.0000

Data Index: 377357 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.1976. Min Act: -0.0000

Data Index: 980586 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.1966. Min Act: -0.0000

Data Index: 568329 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.1963. Min Act: -0.0000

Data Index: 457318 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.1905. Min Act: -0.0000

Data Index: 266623 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.1780. Min Act: -0.0000

Data Index: 425121 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.1898. Min Act: -0.0000

Data Index: 1434851 (Python Code)

Max Activating Token Index: 951

Text #13

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1308869 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.1595. Min Act: -0.0000

Data Index: 44778 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.1674. Min Act: -0.0000

Data Index: 1611596 (Python Code)

Max Activating Token Index: 236

Text #16

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.1658. Min Act: -0.0000

Data Index: 1407517 (Python Code)

Max Activating Token Index: 755

Text #17

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.1770. Min Act: -0.0000

Data Index: 642035 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.1633. Min Act: -0.0000

Data Index: 1579997 (Python Code)

Max Activating Token Index: 684

Text #19

Max Range: 0.3261. Min Range: -0.3261

Max Act: 0.1615. Min Act: -0.0000

Data Index: 419722 (C4 (Web Text))

Max Activating Token Index: 769