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

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

Neuron 4440 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4098. Min Range: -1.4098

Max Act: 1.4098. Min Act: -0.0000

Data Index: 195895 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 1.4098. Min Range: -1.4098

Max Act: 1.1319. Min Act: -0.0000

Data Index: 1110669 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 1.4098. Min Range: -1.4098

Max Act: 1.1957. Min Act: -0.0000

Data Index: 857010 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 1.4098. Min Range: -1.4098

Max Act: 1.1307. Min Act: -0.0000

Data Index: 1173749 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 1.4098. Min Range: -1.4098

Max Act: 1.1197. Min Act: -0.0000

Data Index: 328868 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 1.4098. Min Range: -1.4098

Max Act: 1.0786. Min Act: -0.0000

Data Index: 780666 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 1.4098. Min Range: -1.4098

Max Act: 1.1111. Min Act: -0.0000

Data Index: 706834 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 1.4098. Min Range: -1.4098

Max Act: 0.9523. Min Act: -0.0000

Data Index: 600449 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 1.4098. Min Range: -1.4098

Max Act: 1.0558. Min Act: -0.0000

Data Index: 468163 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 1.4098. Min Range: -1.4098

Max Act: 0.9938. Min Act: -0.0000

Data Index: 1396967 (Python Code)

Max Activating Token Index: 87

Text #10

Max Range: 1.4098. Min Range: -1.4098

Max Act: 0.9597. Min Act: -0.0000

Data Index: 161103 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 1.4098. Min Range: -1.4098

Max Act: 0.9518. Min Act: -0.0000

Data Index: 1477841 (Python Code)

Max Activating Token Index: 267

Text #12

Max Range: 1.4098. Min Range: -1.4098

Max Act: 0.8834. Min Act: -0.0000

Data Index: 1586670 (Python Code)

Max Activating Token Index: 349

Text #13

Max Range: 1.4098. Min Range: -1.4098

Max Act: 0.9424. Min Act: -0.0000

Data Index: 843725 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 1.4098. Min Range: -1.4098

Max Act: 0.8759. Min Act: -0.0000

Data Index: 1421246 (Python Code)

Max Activating Token Index: 216

Text #15

Max Range: 1.4098. Min Range: -1.4098

Max Act: 0.9412. Min Act: -0.0000

Data Index: 1591347 (Python Code)

Max Activating Token Index: 866

Text #16

Max Range: 1.4098. Min Range: -1.4098

Max Act: 0.9400. Min Act: -0.0000

Data Index: 694059 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 1.4098. Min Range: -1.4098

Max Act: 0.9941. Min Act: -0.0000

Data Index: 1576282 (Python Code)

Max Activating Token Index: 585

Text #18

Max Range: 1.4098. Min Range: -1.4098

Max Act: 0.9353. Min Act: -0.0000

Data Index: 1573697 (Python Code)

Max Activating Token Index: 105

Text #19

Max Range: 1.4098. Min Range: -1.4098

Max Act: 0.9809. Min Act: -0.0000

Data Index: 387994 (C4 (Web Text))

Max Activating Token Index: 286