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

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

Neuron 4285 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2901. Min Range: -2.2901

Max Act: 2.2301. Min Act: -0.0000

Data Index: 1649497 (Python Code)

Max Activating Token Index: 176

Text #1

Max Range: 2.2901. Min Range: -2.2901

Max Act: 2.2901. Min Act: -0.0000

Data Index: 1362992 (Python Code)

Max Activating Token Index: 727

Text #2

Max Range: 2.2901. Min Range: -2.2901

Max Act: 1.8657. Min Act: -0.0000

Data Index: 669768 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 2.2901. Min Range: -2.2901

Max Act: 1.7058. Min Act: -0.0000

Data Index: 1504971 (Python Code)

Max Activating Token Index: 461

Text #4

Max Range: 2.2901. Min Range: -2.2901

Max Act: 1.7712. Min Act: -0.0000

Data Index: 1616372 (Python Code)

Max Activating Token Index: 15

Text #5

Max Range: 2.2901. Min Range: -2.2901

Max Act: 1.6457. Min Act: -0.0000

Data Index: 388916 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 2.2901. Min Range: -2.2901

Max Act: 1.8293. Min Act: -0.0000

Data Index: 1606970 (Python Code)

Max Activating Token Index: 15

Text #7

Max Range: 2.2901. Min Range: -2.2901

Max Act: 1.6164. Min Act: -0.0000

Data Index: 1425799 (Python Code)

Max Activating Token Index: 661

Text #8

Max Range: 2.2901. Min Range: -2.2901

Max Act: 1.6800. Min Act: -0.0000

Data Index: 1446769 (Python Code)

Max Activating Token Index: 31

Text #9

Max Range: 2.2901. Min Range: -2.2901

Max Act: 1.5447. Min Act: -0.0000

Data Index: 1501575 (Python Code)

Max Activating Token Index: 390

Text #10

Max Range: 2.2901. Min Range: -2.2901

Max Act: 1.6292. Min Act: 0.0000

Data Index: 1569607 (Python Code)

Max Activating Token Index: 509

Text #11

Max Range: 2.2901. Min Range: -2.2901

Max Act: 1.6096. Min Act: -0.0000

Data Index: 181830 (C4 (Web Text))

Max Activating Token Index: 696

Text #12

Max Range: 2.2901. Min Range: -2.2901

Max Act: 1.6693. Min Act: -0.0000

Data Index: 1426896 (Python Code)

Max Activating Token Index: 339

Text #13

Max Range: 2.2901. Min Range: -2.2901

Max Act: 1.6937. Min Act: -0.0000

Data Index: 1434282 (Python Code)

Max Activating Token Index: 402

Text #14

Max Range: 2.2901. Min Range: -2.2901

Max Act: 1.5452. Min Act: -0.0000

Data Index: 1573950 (Python Code)

Max Activating Token Index: 883

Text #15

Max Range: 2.2901. Min Range: -2.2901

Max Act: 1.6418. Min Act: -0.0000

Data Index: 1532023 (Python Code)

Max Activating Token Index: 684

Text #16

Max Range: 2.2901. Min Range: -2.2901

Max Act: 1.5695. Min Act: -0.0000

Data Index: 1304824 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 2.2901. Min Range: -2.2901

Max Act: 1.6133. Min Act: -0.0000

Data Index: 1506786 (Python Code)

Max Activating Token Index: 548

Text #18

Max Range: 2.2901. Min Range: -2.2901

Max Act: 1.5181. Min Act: -0.0000

Data Index: 1488882 (Python Code)

Max Activating Token Index: 140

Text #19

Max Range: 2.2901. Min Range: -2.2901

Max Act: 1.5556. Min Act: -0.0000

Data Index: 1489043 (Python Code)

Max Activating Token Index: 96