Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1676 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0161. Min Act: -0.0002

Data Index: 19377 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1332493 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1405063 (Python Code)

Max Activating Token Index: 907

Text #3

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1574713 (Python Code)

Max Activating Token Index: 241

Text #4

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0147. Min Act: -0.0002

Data Index: 1510761 (Python Code)

Max Activating Token Index: 568

Text #5

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0138. Min Act: -0.0002

Data Index: 1079635 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1435089 (Python Code)

Max Activating Token Index: 326

Text #7

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0132. Min Act: -0.0002

Data Index: 1348034 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0130. Min Act: -0.0002

Data Index: 439637 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0124. Min Act: -0.0002

Data Index: 1615765 (Python Code)

Max Activating Token Index: 539

Text #10

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0131. Min Act: -0.0002

Data Index: 1548484 (Python Code)

Max Activating Token Index: 804

Text #11

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0119. Min Act: -0.0002

Data Index: 1563542 (Python Code)

Max Activating Token Index: 412

Text #12

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1009914 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0117. Min Act: -0.0002

Data Index: 635798 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0116. Min Act: -0.0002

Data Index: 1448372 (Python Code)

Max Activating Token Index: 294

Text #15

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0117. Min Act: -0.0002

Data Index: 1579717 (Python Code)

Max Activating Token Index: 499

Text #16

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0114. Min Act: -0.0002

Data Index: 1524335 (Python Code)

Max Activating Token Index: 293

Text #17

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0115. Min Act: -0.0002

Data Index: 1570740 (Python Code)

Max Activating Token Index: 289

Text #18

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0117. Min Act: -0.0002

Data Index: 1293506 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.0161. Min Range: -0.0161

Max Act: 0.0118. Min Act: -0.0002

Data Index: 1564881 (Python Code)

Max Activating Token Index: 562