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

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

Neuron 3893 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0439. Min Range: -1.0439

Max Act: 1.0439. Min Act: -0.0001

Data Index: 1347515 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.9016. Min Act: -0.0001

Data Index: 923463 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.7938. Min Act: -0.0001

Data Index: 393585 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.7757. Min Act: -0.0001

Data Index: 644764 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1064459 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.8151. Min Act: -0.0001

Data Index: 971196 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.8308. Min Act: -0.0001

Data Index: 786911 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.7998. Min Act: -0.0001

Data Index: 528885 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.7738. Min Act: -0.0001

Data Index: 165447 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.7062. Min Act: -0.0001

Data Index: 1252655 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.7040. Min Act: -0.0001

Data Index: 317751 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.6844. Min Act: -0.0001

Data Index: 599121 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.6553. Min Act: -0.0001

Data Index: 1087281 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.6756. Min Act: -0.0001

Data Index: 1117083 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.6722. Min Act: -0.0001

Data Index: 529008 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.6714. Min Act: -0.0001

Data Index: 1147477 (C4 (Web Text))

Max Activating Token Index: 474

Text #16

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.6539. Min Act: -0.0001

Data Index: 1090838 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.6087. Min Act: -0.0001

Data Index: 301031 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.6652. Min Act: -0.0001

Data Index: 1205015 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 1.0439. Min Range: -1.0439

Max Act: 0.6635. Min Act: -0.0001

Data Index: 1243255 (C4 (Web Text))

Max Activating Token Index: 114