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

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

Neuron 3393 in Layer 9

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: 0.1357. Min Act: -0.0000

Data Index: 272125 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1287. Min Act: -0.0000

Data Index: 905138 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1276. Min Act: -0.0000

Data Index: 309689 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1163. Min Act: -0.0000

Data Index: 392893 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1561491 (Python Code)

Max Activating Token Index: 356

Text #5

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1103. Min Act: -0.0000

Data Index: 1456260 (Python Code)

Max Activating Token Index: 83

Text #6

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1375513 (Python Code)

Max Activating Token Index: 458

Text #7

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1053. Min Act: -0.0000

Data Index: 1463486 (Python Code)

Max Activating Token Index: 1012

Text #8

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1111. Min Act: -0.0000

Data Index: 1108104 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1035. Min Act: -0.0000

Data Index: 1474794 (Python Code)

Max Activating Token Index: 1014

Text #10

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0952. Min Act: -0.0000

Data Index: 1208338 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1500101 (Python Code)

Max Activating Token Index: 504

Text #12

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1369564 (Python Code)

Max Activating Token Index: 790

Text #13

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1038. Min Act: 0.0000

Data Index: 783470 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0959. Min Act: -0.0000

Data Index: 1560051 (Python Code)

Max Activating Token Index: 823

Text #15

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1163418 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1594573 (Python Code)

Max Activating Token Index: 459

Text #17

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1018. Min Act: 0.0000

Data Index: 1467806 (Python Code)

Max Activating Token Index: 88

Text #18

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0989. Min Act: -0.0000

Data Index: 1438747 (Python Code)

Max Activating Token Index: 903

Text #19

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0993. Min Act: 0.0000

Data Index: 1448419 (Python Code)

Max Activating Token Index: 727