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

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

Neuron 4411 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1724. Min Range: -1.1724

Max Act: 1.1012. Min Act: -0.0000

Data Index: 391659 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 1.1724. Min Range: -1.1724

Max Act: 1.1009. Min Act: -0.0000

Data Index: 1434541 (Python Code)

Max Activating Token Index: 966

Text #2

Max Range: 1.1724. Min Range: -1.1724

Max Act: 1.1724. Min Act: -0.0000

Data Index: 1655719 (Python Code)

Max Activating Token Index: 918

Text #3

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8445. Min Act: -0.0000

Data Index: 301422 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8781. Min Act: -0.0000

Data Index: 1414702 (Python Code)

Max Activating Token Index: 538

Text #5

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8756. Min Act: -0.0000

Data Index: 1075227 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8604. Min Act: -0.0000

Data Index: 968367 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8238. Min Act: -0.0000

Data Index: 1431716 (Python Code)

Max Activating Token Index: 330

Text #8

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8099. Min Act: 0.0000

Data Index: 813079 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.8450. Min Act: -0.0000

Data Index: 294062 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.7260. Min Act: -0.0000

Data Index: 1201832 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.7179. Min Act: -0.0000

Data Index: 1115800 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.6863. Min Act: -0.0000

Data Index: 1022623 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1399723 (Python Code)

Max Activating Token Index: 492

Text #14

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.7031. Min Act: 0.0001

Data Index: 795537 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.6692. Min Act: -0.0000

Data Index: 1563576 (Python Code)

Max Activating Token Index: 126

Text #16

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.6484. Min Act: -0.0000

Data Index: 1427176 (Python Code)

Max Activating Token Index: 456

Text #17

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.6754. Min Act: -0.0000

Data Index: 227979 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.6248. Min Act: -0.0000

Data Index: 161200 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 1.1724. Min Range: -1.1724

Max Act: 0.6977. Min Act: -0.0000

Data Index: 1497487 (Python Code)

Max Activating Token Index: 1015