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

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

Neuron 4152 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: 0.8638. Min Range: -0.8638

Max Act: 0.8638. Min Act: -0.0000

Data Index: 851547 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.7603. Min Act: -0.0000

Data Index: 1230535 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6559. Min Act: -0.0000

Data Index: 484908 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6370. Min Act: -0.0000

Data Index: 937600 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6364. Min Act: -0.0000

Data Index: 957167 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6284. Min Act: -0.0000

Data Index: 1115423 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6172. Min Act: -0.0000

Data Index: 1233550 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.6004. Min Act: -0.0000

Data Index: 633113 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.5902. Min Act: -0.0000

Data Index: 762792 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.5506. Min Act: -0.0000

Data Index: 253203 (C4 (Web Text))

Max Activating Token Index: 853

Text #10

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.5852. Min Act: -0.0000

Data Index: 81901 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.5779. Min Act: -0.0000

Data Index: 606574 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.5606. Min Act: -0.0000

Data Index: 158872 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.5431. Min Act: -0.0000

Data Index: 388442 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.5535. Min Act: -0.0000

Data Index: 211001 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.5211. Min Act: -0.0000

Data Index: 971734 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1084661 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.4907. Min Act: -0.0000

Data Index: 1084524 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.4888. Min Act: -0.0000

Data Index: 873173 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.8638. Min Range: -0.8638

Max Act: 0.5031. Min Act: -0.0000

Data Index: 421245 (C4 (Web Text))

Max Activating Token Index: 316