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

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

Neuron 4454 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2373. Min Act: -0.0002

Data Index: 1435309 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2356. Min Act: -0.0002

Data Index: 1582416 (Python Code)

Max Activating Token Index: 195

Text #2

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2213. Min Act: -0.0002

Data Index: 1587123 (Python Code)

Max Activating Token Index: 128

Text #3

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2183. Min Act: -0.0002

Data Index: 1649739 (Python Code)

Max Activating Token Index: 368

Text #4

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2111. Min Act: -0.0002

Data Index: 1442023 (Python Code)

Max Activating Token Index: 249

Text #5

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2124. Min Act: -0.0002

Data Index: 1635839 (Python Code)

Max Activating Token Index: 297

Text #6

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2107. Min Act: -0.0002

Data Index: 1629413 (Python Code)

Max Activating Token Index: 118

Text #7

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2034. Min Act: -0.0002

Data Index: 1466585 (Python Code)

Max Activating Token Index: 38

Text #8

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2074. Min Act: -0.0002

Data Index: 1537986 (Python Code)

Max Activating Token Index: 86

Text #9

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2008. Min Act: -0.0002

Data Index: 1631593 (Python Code)

Max Activating Token Index: 352

Text #10

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2077. Min Act: -0.0002

Data Index: 1420715 (Python Code)

Max Activating Token Index: 288

Text #11

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2046. Min Act: -0.0002

Data Index: 1530399 (Python Code)

Max Activating Token Index: 744

Text #12

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2037. Min Act: -0.0002

Data Index: 1476256 (Python Code)

Max Activating Token Index: 691

Text #13

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2019. Min Act: -0.0002

Data Index: 1531509 (Python Code)

Max Activating Token Index: 771

Text #14

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2027. Min Act: -0.0002

Data Index: 1631471 (Python Code)

Max Activating Token Index: 383

Text #15

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.2014. Min Act: -0.0002

Data Index: 1391857 (Python Code)

Max Activating Token Index: 284

Text #16

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1938. Min Act: -0.0002

Data Index: 1404202 (Python Code)

Max Activating Token Index: 15

Text #17

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1945. Min Act: -0.0002

Data Index: 1391895 (Python Code)

Max Activating Token Index: 461

Text #18

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1952. Min Act: -0.0002

Data Index: 1406599 (Python Code)

Max Activating Token Index: 445

Text #19

Max Range: 0.2373. Min Range: -0.2373

Max Act: 0.1934. Min Act: -0.0002

Data Index: 1546522 (Python Code)

Max Activating Token Index: 197