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

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

Neuron 4053 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1926. Min Act: -0.0001

Data Index: 157535 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1851. Min Act: -0.0001

Data Index: 1246251 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1805. Min Act: -0.0001

Data Index: 1314801 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1833. Min Act: -0.0001

Data Index: 1287930 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1715. Min Act: -0.0001

Data Index: 65227 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1693. Min Act: -0.0001

Data Index: 403518 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1744. Min Act: -0.0001

Data Index: 288481 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1669. Min Act: -0.0001

Data Index: 699858 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1578. Min Act: -0.0001

Data Index: 1331843 (C4 (Web Text))

Max Activating Token Index: 660

Text #9

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1638. Min Act: -0.0001

Data Index: 243529 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1496. Min Act: -0.0001

Data Index: 245990 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1449. Min Act: -0.0001

Data Index: 56599 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1377. Min Act: -0.0001

Data Index: 1287832 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1433. Min Act: -0.0001

Data Index: 1170073 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1481. Min Act: -0.0001

Data Index: 711951 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1520. Min Act: -0.0001

Data Index: 894014 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1393. Min Act: -0.0001

Data Index: 1246587 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1417. Min Act: -0.0001

Data Index: 284815 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1384. Min Act: -0.0001

Data Index: 101141 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1329. Min Act: -0.0001

Data Index: 620829 (C4 (Web Text))

Max Activating Token Index: 465