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

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

Neuron 3365 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0170. Min Act: -0.0002

Data Index: 1609531 (Python Code)

Max Activating Token Index: 566

Text #1

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1642530 (Python Code)

Max Activating Token Index: 979

Text #2

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1563342 (Python Code)

Max Activating Token Index: 59

Text #3

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0132. Min Act: -0.0002

Data Index: 995137 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0127. Min Act: -0.0002

Data Index: 334928 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0130. Min Act: -0.0002

Data Index: 721620 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1127639 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0122. Min Act: -0.0002

Data Index: 719607 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0127. Min Act: -0.0002

Data Index: 1558610 (Python Code)

Max Activating Token Index: 368

Text #9

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0129. Min Act: -0.0002

Data Index: 1631379 (Python Code)

Max Activating Token Index: 327

Text #10

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0128. Min Act: -0.0002

Data Index: 1513239 (Python Code)

Max Activating Token Index: 252

Text #11

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0119. Min Act: -0.0002

Data Index: 823065 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1517592 (Python Code)

Max Activating Token Index: 719

Text #13

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0120. Min Act: -0.0002

Data Index: 302645 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0113. Min Act: -0.0002

Data Index: 813673 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0117. Min Act: -0.0002

Data Index: 153053 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0108. Min Act: -0.0002

Data Index: 1406459 (Python Code)

Max Activating Token Index: 42

Text #17

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1561857 (Python Code)

Max Activating Token Index: 257

Text #18

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0116. Min Act: -0.0002

Data Index: 545825 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 0.0170. Min Range: -0.0170

Max Act: 0.0111. Min Act: -0.0002

Data Index: 1363999 (Python Code)

Max Activating Token Index: 320