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

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

Neuron 4013 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.7288. Min Act: -0.0001

Data Index: 1416021 (Python Code)

Max Activating Token Index: 71

Text #1

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.7391. Min Act: -0.0001

Data Index: 1486867 (Python Code)

Max Activating Token Index: 55

Text #2

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.7129. Min Act: -0.0001

Data Index: 1432730 (Python Code)

Max Activating Token Index: 188

Text #3

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.7026. Min Act: -0.0001

Data Index: 1412801 (Python Code)

Max Activating Token Index: 217

Text #4

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6145. Min Act: -0.0001

Data Index: 1525697 (Python Code)

Max Activating Token Index: 136

Text #5

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6851. Min Act: -0.0001

Data Index: 1581284 (Python Code)

Max Activating Token Index: 333

Text #6

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6496. Min Act: -0.0001

Data Index: 1442997 (Python Code)

Max Activating Token Index: 137

Text #7

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6682. Min Act: -0.0001

Data Index: 1388519 (Python Code)

Max Activating Token Index: 587

Text #8

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6857. Min Act: -0.0001

Data Index: 1470672 (Python Code)

Max Activating Token Index: 219

Text #9

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6496. Min Act: -0.0001

Data Index: 1440100 (Python Code)

Max Activating Token Index: 90

Text #10

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5960. Min Act: -0.0001

Data Index: 1630229 (Python Code)

Max Activating Token Index: 151

Text #11

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5894. Min Act: -0.0001

Data Index: 1628813 (Python Code)

Max Activating Token Index: 42

Text #12

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6240. Min Act: -0.0001

Data Index: 1510749 (Python Code)

Max Activating Token Index: 320

Text #13

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6035. Min Act: -0.0001

Data Index: 1480072 (Python Code)

Max Activating Token Index: 223

Text #14

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6209. Min Act: -0.0001

Data Index: 1486593 (Python Code)

Max Activating Token Index: 324

Text #15

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6165. Min Act: -0.0001

Data Index: 1431861 (Python Code)

Max Activating Token Index: 697

Text #16

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6247. Min Act: -0.0001

Data Index: 1427239 (Python Code)

Max Activating Token Index: 169

Text #17

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.6113. Min Act: -0.0001

Data Index: 1450765 (Python Code)

Max Activating Token Index: 601

Text #18

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5870. Min Act: -0.0001

Data Index: 1375390 (Python Code)

Max Activating Token Index: 625

Text #19

Max Range: 0.7391. Min Range: -0.7391

Max Act: 0.5898. Min Act: -0.0001

Data Index: 1526493 (Python Code)

Max Activating Token Index: 35