Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 991 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.8348. Min Act: -0.0002

Data Index: 1578791 (Python Code)

Max Activating Token Index: 109

Text #1

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.5680. Min Act: -0.0002

Data Index: 1651956 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.3734. Min Act: -0.0002

Data Index: 1518371 (Python Code)

Max Activating Token Index: 18

Text #3

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.3005. Min Act: -0.0002

Data Index: 1409372 (Python Code)

Max Activating Token Index: 13

Text #4

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.3071. Min Act: -0.0002

Data Index: 1435685 (Python Code)

Max Activating Token Index: 592

Text #5

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.4282. Min Act: -0.0002

Data Index: 1403137 (Python Code)

Max Activating Token Index: 794

Text #6

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.3014. Min Act: -0.0002

Data Index: 1639016 (Python Code)

Max Activating Token Index: 14

Text #7

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.1812. Min Act: -0.0002

Data Index: 1411645 (Python Code)

Max Activating Token Index: 121

Text #8

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.3228. Min Act: -0.0002

Data Index: 1441975 (Python Code)

Max Activating Token Index: 45

Text #9

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.1541. Min Act: -0.0002

Data Index: 1545278 (Python Code)

Max Activating Token Index: 869

Text #10

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.2269. Min Act: -0.0002

Data Index: 1577733 (Python Code)

Max Activating Token Index: 215

Text #11

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.1779. Min Act: -0.0002

Data Index: 1376342 (Python Code)

Max Activating Token Index: 402

Text #12

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.2168. Min Act: -0.0002

Data Index: 1635081 (Python Code)

Max Activating Token Index: 45

Text #13

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.2527. Min Act: -0.0002

Data Index: 1624472 (Python Code)

Max Activating Token Index: 42

Text #14

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.1846. Min Act: -0.0002

Data Index: 1648657 (Python Code)

Max Activating Token Index: 330

Text #15

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.1720. Min Act: -0.0002

Data Index: 1505294 (Python Code)

Max Activating Token Index: 27

Text #16

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.1643. Min Act: -0.0002

Data Index: 1568336 (Python Code)

Max Activating Token Index: 41

Text #17

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.1905. Min Act: -0.0002

Data Index: 1624498 (Python Code)

Max Activating Token Index: 145

Text #18

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.2608. Min Act: -0.0002

Data Index: 1579589 (Python Code)

Max Activating Token Index: 165

Text #19

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.1547. Min Act: -0.0002

Data Index: 1364556 (Python Code)

Max Activating Token Index: 74