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

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

Neuron 2644 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1433. Min Act: -0.0000

Data Index: 616523 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1358. Min Act: -0.0000

Data Index: 936769 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1180. Min Act: -0.0000

Data Index: 438769 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1223. Min Act: -0.0001

Data Index: 541187 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1194. Min Act: -0.0000

Data Index: 660411 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.1002. Min Act: -0.0000

Data Index: 599835 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0986. Min Act: -0.0000

Data Index: 547648 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0993. Min Act: -0.0000

Data Index: 542465 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0925. Min Act: -0.0000

Data Index: 31097 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0859. Min Act: -0.0000

Data Index: 671569 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0883. Min Act: -0.0000

Data Index: 188331 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0892. Min Act: -0.0000

Data Index: 891322 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0859. Min Act: -0.0000

Data Index: 406073 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0860. Min Act: -0.0000

Data Index: 314143 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0840. Min Act: -0.0000

Data Index: 1094252 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0876. Min Act: -0.0000

Data Index: 1536545 (Python Code)

Max Activating Token Index: 256

Text #16

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0759. Min Act: -0.0000

Data Index: 83619 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0838. Min Act: -0.0000

Data Index: 1003342 (C4 (Web Text))

Max Activating Token Index: 75

Text #18

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0831. Min Act: -0.0000

Data Index: 328347 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 0.1433. Min Range: -0.1433

Max Act: 0.0695. Min Act: -0.0000

Data Index: 766060 (C4 (Web Text))

Max Activating Token Index: 260