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

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

Neuron 349 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0035. Min Act: -0.0001

Data Index: 191195 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0028. Min Act: -0.0000

Data Index: 1645285 (Python Code)

Max Activating Token Index: 33

Text #2

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0026. Min Act: -0.0001

Data Index: 176365 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0026. Min Act: -0.0000

Data Index: 1460402 (Python Code)

Max Activating Token Index: 597

Text #4

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0020. Min Act: -0.0000

Data Index: 1607334 (Python Code)

Max Activating Token Index: 21

Text #5

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0018. Min Act: -0.0000

Data Index: 1471017 (Python Code)

Max Activating Token Index: 997

Text #6

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0020. Min Act: -0.0000

Data Index: 475405 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0019. Min Act: -0.0000

Data Index: 1386025 (Python Code)

Max Activating Token Index: 504

Text #8

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0017. Min Act: -0.0000

Data Index: 1340180 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0017. Min Act: -0.0000

Data Index: 938370 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0013. Min Act: -0.0000

Data Index: 1449158 (Python Code)

Max Activating Token Index: 235

Text #11

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0016. Min Act: -0.0000

Data Index: 1554302 (Python Code)

Max Activating Token Index: 491

Text #12

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0015. Min Act: -0.0000

Data Index: 469324 (C4 (Web Text))

Max Activating Token Index: 892

Text #13

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0013. Min Act: -0.0000

Data Index: 1447801 (Python Code)

Max Activating Token Index: 135

Text #14

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0014. Min Act: -0.0000

Data Index: 1581003 (Python Code)

Max Activating Token Index: 543

Text #15

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0015. Min Act: -0.0001

Data Index: 1279658 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0010. Min Act: -0.0001

Data Index: 1218738 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0014. Min Act: -0.0000

Data Index: 356025 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0014. Min Act: -0.0000

Data Index: 1548938 (Python Code)

Max Activating Token Index: 31

Text #19

Max Range: 0.0035. Min Range: -0.0035

Max Act: 0.0015. Min Act: -0.0000

Data Index: 1550132 (Python Code)

Max Activating Token Index: 298