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

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

Neuron 3023 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: 0.1357. Min Range: -0.1357

Max Act: 0.1347. Min Act: -0.0002

Data Index: 1639630 (Python Code)

Max Activating Token Index: 957

Text #1

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1340. Min Act: -0.0002

Data Index: 1375213 (Python Code)

Max Activating Token Index: 204

Text #2

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1357. Min Act: -0.0002

Data Index: 1598209 (Python Code)

Max Activating Token Index: 573

Text #3

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1133. Min Act: -0.0002

Data Index: 1608132 (Python Code)

Max Activating Token Index: 783

Text #4

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1108. Min Act: -0.0002

Data Index: 1519328 (Python Code)

Max Activating Token Index: 198

Text #5

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1110. Min Act: -0.0002

Data Index: 1431568 (Python Code)

Max Activating Token Index: 984

Text #6

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1119. Min Act: -0.0002

Data Index: 1459656 (Python Code)

Max Activating Token Index: 489

Text #7

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1082. Min Act: -0.0002

Data Index: 1403596 (Python Code)

Max Activating Token Index: 421

Text #8

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1125. Min Act: -0.0002

Data Index: 1376829 (Python Code)

Max Activating Token Index: 392

Text #9

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1076. Min Act: -0.0002

Data Index: 1510308 (Python Code)

Max Activating Token Index: 936

Text #10

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1017. Min Act: -0.0002

Data Index: 1652019 (Python Code)

Max Activating Token Index: 886

Text #11

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1019. Min Act: -0.0002

Data Index: 1568085 (Python Code)

Max Activating Token Index: 824

Text #12

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1009. Min Act: -0.0002

Data Index: 1432797 (Python Code)

Max Activating Token Index: 353

Text #13

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0927. Min Act: -0.0002

Data Index: 1469592 (Python Code)

Max Activating Token Index: 393

Text #14

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0991. Min Act: -0.0002

Data Index: 1480791 (Python Code)

Max Activating Token Index: 374

Text #15

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1016. Min Act: -0.0002

Data Index: 1506410 (Python Code)

Max Activating Token Index: 901

Text #16

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1008. Min Act: -0.0002

Data Index: 1420774 (Python Code)

Max Activating Token Index: 915

Text #17

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1005. Min Act: -0.0002

Data Index: 1381985 (Python Code)

Max Activating Token Index: 159

Text #18

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0986. Min Act: -0.0002

Data Index: 1456685 (Python Code)

Max Activating Token Index: 599

Text #19

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0991. Min Act: -0.0002

Data Index: 1614484 (Python Code)

Max Activating Token Index: 388