Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2532 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2191. Min Act: -0.0001

Data Index: 1524511 (Python Code)

Max Activating Token Index: 79

Text #1

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2470. Min Act: -0.0001

Data Index: 1429990 (Python Code)

Max Activating Token Index: 603

Text #2

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2139. Min Act: -0.0001

Data Index: 1652799 (Python Code)

Max Activating Token Index: 826

Text #3

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1761. Min Act: -0.0001

Data Index: 1555983 (Python Code)

Max Activating Token Index: 342

Text #4

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1931. Min Act: -0.0001

Data Index: 1519666 (Python Code)

Max Activating Token Index: 253

Text #5

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.2108. Min Act: -0.0001

Data Index: 1632507 (Python Code)

Max Activating Token Index: 629

Text #6

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1955. Min Act: -0.0001

Data Index: 1435871 (Python Code)

Max Activating Token Index: 113

Text #7

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1956. Min Act: -0.0001

Data Index: 1430364 (Python Code)

Max Activating Token Index: 520

Text #8

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1810. Min Act: -0.0001

Data Index: 1577437 (Python Code)

Max Activating Token Index: 171

Text #9

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1747. Min Act: -0.0001

Data Index: 1616916 (Python Code)

Max Activating Token Index: 60

Text #10

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1802. Min Act: -0.0001

Data Index: 1372866 (Python Code)

Max Activating Token Index: 20

Text #11

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1816. Min Act: -0.0001

Data Index: 297436 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1884. Min Act: -0.0001

Data Index: 1368281 (Python Code)

Max Activating Token Index: 19

Text #13

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1785. Min Act: -0.0001

Data Index: 1121122 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1765. Min Act: -0.0000

Data Index: 1434555 (Python Code)

Max Activating Token Index: 52

Text #15

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1679. Min Act: -0.0001

Data Index: 1572363 (Python Code)

Max Activating Token Index: 669

Text #16

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1567. Min Act: 0.0000

Data Index: 1416308 (Python Code)

Max Activating Token Index: 36

Text #17

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1806. Min Act: -0.0001

Data Index: 1623337 (Python Code)

Max Activating Token Index: 427

Text #18

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1794. Min Act: -0.0001

Data Index: 1382255 (Python Code)

Max Activating Token Index: 23

Text #19

Max Range: 0.2470. Min Range: -0.2470

Max Act: 0.1721. Min Act: -0.0001

Data Index: 78490 (C4 (Web Text))

Max Activating Token Index: 755