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

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

Neuron 4596 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: 0.0032. Min Range: -0.0032

Max Act: 0.0032. Min Act: -0.0001

Data Index: 191195 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0027. Min Act: -0.0000

Data Index: 1447801 (Python Code)

Max Activating Token Index: 135

Text #2

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0028. Min Act: -0.0000

Data Index: 469324 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0021. Min Act: -0.0000

Data Index: 1461144 (Python Code)

Max Activating Token Index: 616

Text #4

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0025. Min Act: -0.0000

Data Index: 475405 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0022. Min Act: -0.0001

Data Index: 176365 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0017. Min Act: -0.0000

Data Index: 1483938 (Python Code)

Max Activating Token Index: 131

Text #7

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0022. Min Act: -0.0000

Data Index: 1632489 (Python Code)

Max Activating Token Index: 606

Text #8

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0020. Min Act: -0.0000

Data Index: 1137682 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0020. Min Act: -0.0000

Data Index: 1396762 (Python Code)

Max Activating Token Index: 952

Text #10

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0021. Min Act: -0.0000

Data Index: 1526189 (Python Code)

Max Activating Token Index: 115

Text #11

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0021. Min Act: -0.0000

Data Index: 1550769 (Python Code)

Max Activating Token Index: 348

Text #12

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0011. Min Act: -0.0000

Data Index: 1470290 (Python Code)

Max Activating Token Index: 294

Text #13

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0015. Min Act: -0.0000

Data Index: 767153 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0015. Min Act: -0.0000

Data Index: 1612216 (Python Code)

Max Activating Token Index: 476

Text #15

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0012. Min Act: -0.0000

Data Index: 228614 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0014. Min Act: -0.0000

Data Index: 938370 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0014. Min Act: -0.0000

Data Index: 1627961 (Python Code)

Max Activating Token Index: 200

Text #18

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0013. Min Act: -0.0000

Data Index: 356025 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0012. Min Act: -0.0000

Data Index: 130567 (C4 (Web Text))

Max Activating Token Index: 1022