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

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

Neuron 1958 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3096. Min Range: -2.3096

Max Act: 2.0827. Min Act: -0.0000

Data Index: 1388626 (Python Code)

Max Activating Token Index: 592

Text #1

Max Range: 2.3096. Min Range: -2.3096

Max Act: 2.3096. Min Act: -0.0000

Data Index: 1484066 (Python Code)

Max Activating Token Index: 583

Text #2

Max Range: 2.3096. Min Range: -2.3096

Max Act: 2.1677. Min Act: -0.0000

Data Index: 1513763 (Python Code)

Max Activating Token Index: 396

Text #3

Max Range: 2.3096. Min Range: -2.3096

Max Act: 1.9851. Min Act: -0.0000

Data Index: 1486585 (Python Code)

Max Activating Token Index: 550

Text #4

Max Range: 2.3096. Min Range: -2.3096

Max Act: 2.1644. Min Act: -0.0000

Data Index: 1544097 (Python Code)

Max Activating Token Index: 312

Text #5

Max Range: 2.3096. Min Range: -2.3096

Max Act: 2.1728. Min Act: -0.0000

Data Index: 1537197 (Python Code)

Max Activating Token Index: 358

Text #6

Max Range: 2.3096. Min Range: -2.3096

Max Act: 1.6798. Min Act: -0.0000

Data Index: 1603887 (Python Code)

Max Activating Token Index: 832

Text #7

Max Range: 2.3096. Min Range: -2.3096

Max Act: 1.9844. Min Act: -0.0000

Data Index: 1463148 (Python Code)

Max Activating Token Index: 213

Text #8

Max Range: 2.3096. Min Range: -2.3096

Max Act: 2.0290. Min Act: -0.0000

Data Index: 1488038 (Python Code)

Max Activating Token Index: 221

Text #9

Max Range: 2.3096. Min Range: -2.3096

Max Act: 1.6097. Min Act: -0.0000

Data Index: 1461772 (Python Code)

Max Activating Token Index: 211

Text #10

Max Range: 2.3096. Min Range: -2.3096

Max Act: 1.7597. Min Act: -0.0000

Data Index: 1558765 (Python Code)

Max Activating Token Index: 899

Text #11

Max Range: 2.3096. Min Range: -2.3096

Max Act: 1.8541. Min Act: -0.0000

Data Index: 1441771 (Python Code)

Max Activating Token Index: 810

Text #12

Max Range: 2.3096. Min Range: -2.3096

Max Act: 1.8643. Min Act: -0.0000

Data Index: 1366156 (Python Code)

Max Activating Token Index: 149

Text #13

Max Range: 2.3096. Min Range: -2.3096

Max Act: 1.7460. Min Act: -0.0001

Data Index: 1634828 (Python Code)

Max Activating Token Index: 287

Text #14

Max Range: 2.3096. Min Range: -2.3096

Max Act: 1.8336. Min Act: -0.0000

Data Index: 1469258 (Python Code)

Max Activating Token Index: 439

Text #15

Max Range: 2.3096. Min Range: -2.3096

Max Act: 1.8274. Min Act: -0.0000

Data Index: 1542264 (Python Code)

Max Activating Token Index: 87

Text #16

Max Range: 2.3096. Min Range: -2.3096

Max Act: 1.9117. Min Act: -0.0000

Data Index: 1637939 (Python Code)

Max Activating Token Index: 387

Text #17

Max Range: 2.3096. Min Range: -2.3096

Max Act: 1.6934. Min Act: -0.0000

Data Index: 1507786 (Python Code)

Max Activating Token Index: 573

Text #18

Max Range: 2.3096. Min Range: -2.3096

Max Act: 1.7846. Min Act: -0.0000

Data Index: 1652758 (Python Code)

Max Activating Token Index: 425

Text #19

Max Range: 2.3096. Min Range: -2.3096

Max Act: 2.1006. Min Act: -0.0000

Data Index: 1533649 (Python Code)

Max Activating Token Index: 217