Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2654 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.8333. Min Act: -0.0003

Data Index: 1476229 (Python Code)

Max Activating Token Index: 911

Text #1

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.8210. Min Act: -0.0003

Data Index: 1359878 (Python Code)

Max Activating Token Index: 461

Text #2

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.8441. Min Act: -0.0003

Data Index: 1478482 (Python Code)

Max Activating Token Index: 881

Text #3

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.8282. Min Act: -0.0003

Data Index: 1400805 (Python Code)

Max Activating Token Index: 732

Text #4

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7824. Min Act: -0.0003

Data Index: 1562493 (Python Code)

Max Activating Token Index: 619

Text #5

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7371. Min Act: -0.0003

Data Index: 1592877 (Python Code)

Max Activating Token Index: 306

Text #6

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7031. Min Act: -0.0003

Data Index: 1536539 (Python Code)

Max Activating Token Index: 505

Text #7

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6632. Min Act: -0.0003

Data Index: 1503764 (Python Code)

Max Activating Token Index: 462

Text #8

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6313. Min Act: -0.0003

Data Index: 1618879 (Python Code)

Max Activating Token Index: 467

Text #9

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6134. Min Act: -0.0003

Data Index: 1561564 (Python Code)

Max Activating Token Index: 1020

Text #10

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6245. Min Act: -0.0003

Data Index: 1570358 (Python Code)

Max Activating Token Index: 656

Text #11

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6202. Min Act: -0.0003

Data Index: 1512568 (Python Code)

Max Activating Token Index: 443

Text #12

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6156. Min Act: -0.0003

Data Index: 1564728 (Python Code)

Max Activating Token Index: 497

Text #13

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6128. Min Act: -0.0003

Data Index: 1547707 (Python Code)

Max Activating Token Index: 211

Text #14

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.5876. Min Act: -0.0003

Data Index: 1653681 (Python Code)

Max Activating Token Index: 460

Text #15

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6193. Min Act: -0.0003

Data Index: 1539519 (Python Code)

Max Activating Token Index: 513

Text #16

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6128. Min Act: -0.0003

Data Index: 1645151 (Python Code)

Max Activating Token Index: 827

Text #17

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.5981. Min Act: -0.0003

Data Index: 1430672 (Python Code)

Max Activating Token Index: 336

Text #18

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.5739. Min Act: -0.0003

Data Index: 1513762 (Python Code)

Max Activating Token Index: 452

Text #19

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.5487. Min Act: -0.0003

Data Index: 1514179 (Python Code)

Max Activating Token Index: 798