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

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

Neuron 1282 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: 1.1256. Min Range: -1.1256

Max Act: 1.1256. Min Act: -0.0000

Data Index: 1461717 (Python Code)

Max Activating Token Index: 184

Text #1

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.9759. Min Act: -0.0000

Data Index: 1520311 (Python Code)

Max Activating Token Index: 603

Text #2

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.9757. Min Act: -0.0000

Data Index: 551810 (C4 (Web Text))

Max Activating Token Index: 593

Text #3

Max Range: 1.1256. Min Range: -1.1256

Max Act: 1.0781. Min Act: -0.0000

Data Index: 1296446 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.8124. Min Act: -0.0000

Data Index: 38468 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.8011. Min Act: -0.0000

Data Index: 168051 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.8000. Min Act: -0.0000

Data Index: 625948 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.7803. Min Act: -0.0000

Data Index: 929482 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.7087. Min Act: -0.0000

Data Index: 396242 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.7157. Min Act: -0.0000

Data Index: 780512 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.5985. Min Act: -0.0000

Data Index: 616617 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.6073. Min Act: -0.0000

Data Index: 677147 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.5867. Min Act: -0.0000

Data Index: 324790 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.5511. Min Act: -0.0000

Data Index: 194788 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.5857. Min Act: -0.0000

Data Index: 620962 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.5728. Min Act: -0.0000

Data Index: 817988 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.5289. Min Act: -0.0000

Data Index: 1160124 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.5669. Min Act: -0.0000

Data Index: 1203553 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1590879 (Python Code)

Max Activating Token Index: 101

Text #19

Max Range: 1.1256. Min Range: -1.1256

Max Act: 0.5494. Min Act: -0.0000

Data Index: 658728 (C4 (Web Text))

Max Activating Token Index: 989