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

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

Neuron 3221 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0169. Min Act: -0.0003

Data Index: 133524 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0149. Min Act: -0.0003

Data Index: 861290 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0143. Min Act: -0.0003

Data Index: 309345 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0145. Min Act: -0.0003

Data Index: 1632363 (Python Code)

Max Activating Token Index: 572

Text #4

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0141. Min Act: -0.0003

Data Index: 1622527 (Python Code)

Max Activating Token Index: 175

Text #5

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0138. Min Act: -0.0003

Data Index: 1455397 (Python Code)

Max Activating Token Index: 530

Text #6

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0134. Min Act: -0.0003

Data Index: 614188 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0131. Min Act: -0.0003

Data Index: 860559 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0138. Min Act: -0.0003

Data Index: 691540 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0132. Min Act: -0.0002

Data Index: 1653057 (Python Code)

Max Activating Token Index: 327

Text #10

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0129. Min Act: -0.0003

Data Index: 1598836 (Python Code)

Max Activating Token Index: 656

Text #11

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0131. Min Act: -0.0003

Data Index: 1456994 (Python Code)

Max Activating Token Index: 50

Text #12

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0131. Min Act: -0.0003

Data Index: 1535792 (Python Code)

Max Activating Token Index: 864

Text #13

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0127. Min Act: -0.0003

Data Index: 1535727 (Python Code)

Max Activating Token Index: 747

Text #14

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0130. Min Act: -0.0003

Data Index: 1127483 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0128. Min Act: -0.0003

Data Index: 366772 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0129. Min Act: -0.0003

Data Index: 1360808 (Python Code)

Max Activating Token Index: 11

Text #17

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0132. Min Act: -0.0003

Data Index: 1380325 (Python Code)

Max Activating Token Index: 689

Text #18

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0128. Min Act: -0.0003

Data Index: 1417853 (Python Code)

Max Activating Token Index: 33

Text #19

Max Range: 0.0169. Min Range: -0.0169

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1453632 (Python Code)

Max Activating Token Index: 510