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

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

Neuron 4909 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: 1.7302. Min Range: -1.7302

Max Act: 1.7302. Min Act: -0.0002

Data Index: 1442005 (Python Code)

Max Activating Token Index: 24

Text #1

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.5435. Min Act: -0.0002

Data Index: 1484094 (Python Code)

Max Activating Token Index: 9

Text #2

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.6221. Min Act: -0.0002

Data Index: 1471292 (Python Code)

Max Activating Token Index: 13

Text #3

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.6227. Min Act: -0.0002

Data Index: 1469916 (Python Code)

Max Activating Token Index: 22

Text #4

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.5727. Min Act: -0.0002

Data Index: 1513863 (Python Code)

Max Activating Token Index: 10

Text #5

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.5341. Min Act: -0.0002

Data Index: 1366943 (Python Code)

Max Activating Token Index: 11

Text #6

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.4892. Min Act: -0.0002

Data Index: 1538496 (Python Code)

Max Activating Token Index: 14

Text #7

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.4831. Min Act: -0.0002

Data Index: 1629992 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.5655. Min Act: -0.0002

Data Index: 1579642 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.4339. Min Act: -0.0002

Data Index: 1631900 (Python Code)

Max Activating Token Index: 12

Text #10

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.4562. Min Act: -0.0002

Data Index: 1586658 (Python Code)

Max Activating Token Index: 9

Text #11

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.4386. Min Act: -0.0002

Data Index: 1408148 (Python Code)

Max Activating Token Index: 23

Text #12

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.4721. Min Act: -0.0002

Data Index: 1377812 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.4129. Min Act: -0.0002

Data Index: 1394045 (Python Code)

Max Activating Token Index: 7

Text #14

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.4506. Min Act: -0.0002

Data Index: 1590641 (Python Code)

Max Activating Token Index: 11

Text #15

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.4674. Min Act: -0.0002

Data Index: 1576940 (Python Code)

Max Activating Token Index: 7

Text #16

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.4108. Min Act: -0.0002

Data Index: 1447068 (Python Code)

Max Activating Token Index: 12

Text #17

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.3996. Min Act: -0.0002

Data Index: 1476249 (Python Code)

Max Activating Token Index: 21

Text #18

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.2539. Min Act: -0.0002

Data Index: 1372869 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 1.7302. Min Range: -1.7302

Max Act: 1.3519. Min Act: -0.0002

Data Index: 1398466 (Python Code)

Max Activating Token Index: 6