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

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

Neuron 13 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: 1.0418. Min Range: -1.0418

Max Act: 1.0418. Min Act: -0.0001

Data Index: 51227 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.7909. Min Act: -0.0000

Data Index: 88508 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.8133. Min Act: -0.0000

Data Index: 655177 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.8051. Min Act: -0.0000

Data Index: 617142 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.7773. Min Act: -0.0000

Data Index: 572768 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.8205. Min Act: -0.0000

Data Index: 682601 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.7387. Min Act: -0.0000

Data Index: 299418 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.7748. Min Act: -0.0000

Data Index: 1308739 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.6841. Min Act: -0.0000

Data Index: 778814 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.7007. Min Act: -0.0000

Data Index: 604064 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.7140. Min Act: -0.0000

Data Index: 617293 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.7354. Min Act: -0.0000

Data Index: 56506 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.7298. Min Act: -0.0000

Data Index: 439361 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1093279 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1132203 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.6945. Min Act: -0.0000

Data Index: 576711 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.6496. Min Act: -0.0000

Data Index: 1325113 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.6793. Min Act: -0.0000

Data Index: 511103 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.6742. Min Act: -0.0000

Data Index: 252258 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 1.0418. Min Range: -1.0418

Max Act: 0.7010. Min Act: -0.0000

Data Index: 1231815 (C4 (Web Text))

Max Activating Token Index: 151