Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 778 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0168. Min Act: -0.0006

Data Index: 137583 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0153. Min Act: -0.0006

Data Index: 1023648 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0150. Min Act: -0.0006

Data Index: 1365665 (Python Code)

Max Activating Token Index: 952

Text #3

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0131. Min Act: -0.0006

Data Index: 190915 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0133. Min Act: -0.0006

Data Index: 1167724 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0131. Min Act: -0.0006

Data Index: 547912 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0124. Min Act: -0.0006

Data Index: 417400 (C4 (Web Text))

Max Activating Token Index: 746

Text #7

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0125. Min Act: -0.0005

Data Index: 1386863 (Python Code)

Max Activating Token Index: 36

Text #8

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0117. Min Act: -0.0006

Data Index: 899217 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0117. Min Act: -0.0006

Data Index: 957180 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0119. Min Act: -0.0006

Data Index: 805817 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0116. Min Act: -0.0005

Data Index: 1378744 (Python Code)

Max Activating Token Index: 76

Text #12

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0114. Min Act: -0.0006

Data Index: 1618744 (Python Code)

Max Activating Token Index: 833

Text #13

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0114. Min Act: -0.0006

Data Index: 1286470 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0111. Min Act: -0.0005

Data Index: 1360640 (Python Code)

Max Activating Token Index: 431

Text #15

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0114. Min Act: -0.0006

Data Index: 1637670 (Python Code)

Max Activating Token Index: 75

Text #16

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0115. Min Act: -0.0005

Data Index: 1443928 (Python Code)

Max Activating Token Index: 67

Text #17

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0115. Min Act: -0.0006

Data Index: 542513 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0115. Min Act: -0.0006

Data Index: 1645618 (Python Code)

Max Activating Token Index: 533

Text #19

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0112. Min Act: -0.0005

Data Index: 1526814 (Python Code)

Max Activating Token Index: 246