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

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

Neuron 752 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5923. Min Act: -0.0000

Data Index: 1620368 (Python Code)

Max Activating Token Index: 481

Text #1

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.0782. Min Act: -0.0000

Data Index: 1514694 (Python Code)

Max Activating Token Index: 584

Text #2

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.0366. Min Act: -0.0000

Data Index: 1575790 (Python Code)

Max Activating Token Index: 937

Text #3

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.0013. Min Act: -0.0001

Data Index: 1594542 (Python Code)

Max Activating Token Index: 144

Text #4

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.0384. Min Act: -0.0000

Data Index: 1421580 (Python Code)

Max Activating Token Index: 425

Text #5

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.0000. Min Act: -0.0000

Data Index: 1648286 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.0214. Min Act: -0.0000

Data Index: 1428394 (Python Code)

Max Activating Token Index: 209

Text #7

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.0001. Min Act: -0.0000

Data Index: 1640098 (Python Code)

Max Activating Token Index: 176

Text #8

Max Range: 1.5923. Min Range: -1.5923

Max Act: 0.9969. Min Act: -0.0000

Data Index: 1390875 (Python Code)

Max Activating Token Index: 260

Text #9

Max Range: 1.5923. Min Range: -1.5923

Max Act: 0.9931. Min Act: -0.0000

Data Index: 1434760 (Python Code)

Max Activating Token Index: 394

Text #10

Max Range: 1.5923. Min Range: -1.5923

Max Act: 0.9184. Min Act: -0.0000

Data Index: 1538133 (Python Code)

Max Activating Token Index: 494

Text #11

Max Range: 1.5923. Min Range: -1.5923

Max Act: 0.9725. Min Act: -0.0000

Data Index: 1622248 (Python Code)

Max Activating Token Index: 884

Text #12

Max Range: 1.5923. Min Range: -1.5923

Max Act: 0.9909. Min Act: -0.0000

Data Index: 1656790 (Python Code)

Max Activating Token Index: 991

Text #13

Max Range: 1.5923. Min Range: -1.5923

Max Act: 0.9641. Min Act: -0.0000

Data Index: 1460111 (Python Code)

Max Activating Token Index: 326

Text #14

Max Range: 1.5923. Min Range: -1.5923

Max Act: 0.9400. Min Act: -0.0000

Data Index: 1427349 (Python Code)

Max Activating Token Index: 760

Text #15

Max Range: 1.5923. Min Range: -1.5923

Max Act: 0.9630. Min Act: -0.0000

Data Index: 1403913 (Python Code)

Max Activating Token Index: 631

Text #16

Max Range: 1.5923. Min Range: -1.5923

Max Act: 0.9294. Min Act: -0.0000

Data Index: 1404298 (Python Code)

Max Activating Token Index: 328

Text #17

Max Range: 1.5923. Min Range: -1.5923

Max Act: 0.9895. Min Act: -0.0000

Data Index: 1459275 (Python Code)

Max Activating Token Index: 900

Text #18

Max Range: 1.5923. Min Range: -1.5923

Max Act: 0.9265. Min Act: -0.0000

Data Index: 1520083 (Python Code)

Max Activating Token Index: 254

Text #19

Max Range: 1.5923. Min Range: -1.5923

Max Act: 0.9265. Min Act: -0.0000

Data Index: 1562437 (Python Code)

Max Activating Token Index: 468