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

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

Neuron 5454 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: 0.2181. Min Range: -0.2181

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1403371 (Python Code)

Max Activating Token Index: 81

Text #1

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.2181. Min Act: -0.0000

Data Index: 90834 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1966. Min Act: -0.0000

Data Index: 1611808 (Python Code)

Max Activating Token Index: 56

Text #3

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1500120 (Python Code)

Max Activating Token Index: 310

Text #4

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1489356 (Python Code)

Max Activating Token Index: 870

Text #5

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1848. Min Act: -0.0000

Data Index: 944742 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1878. Min Act: -0.0000

Data Index: 1597301 (Python Code)

Max Activating Token Index: 537

Text #7

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1806. Min Act: -0.0000

Data Index: 1609796 (Python Code)

Max Activating Token Index: 72

Text #8

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1715. Min Act: -0.0000

Data Index: 1387050 (Python Code)

Max Activating Token Index: 797

Text #9

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1567527 (Python Code)

Max Activating Token Index: 421

Text #10

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1879. Min Act: -0.0000

Data Index: 1399010 (Python Code)

Max Activating Token Index: 253

Text #11

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1744. Min Act: -0.0000

Data Index: 1361503 (Python Code)

Max Activating Token Index: 64

Text #12

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1739. Min Act: -0.0000

Data Index: 1386452 (Python Code)

Max Activating Token Index: 983

Text #13

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1860. Min Act: -0.0000

Data Index: 1152114 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1586862 (Python Code)

Max Activating Token Index: 404

Text #15

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1728. Min Act: -0.0000

Data Index: 292494 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1791. Min Act: -0.0000

Data Index: 1527346 (Python Code)

Max Activating Token Index: 413

Text #17

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1776. Min Act: -0.0000

Data Index: 1518503 (Python Code)

Max Activating Token Index: 287

Text #18

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1774. Min Act: -0.0000

Data Index: 1610892 (Python Code)

Max Activating Token Index: 152

Text #19

Max Range: 0.2181. Min Range: -0.2181

Max Act: 0.1771. Min Act: -0.0000

Data Index: 1371215 (Python Code)

Max Activating Token Index: 938