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

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

Neuron 5046 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1556. Min Range: -1.1556

Max Act: 1.1556. Min Act: -0.0001

Data Index: 909632 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.9330. Min Act: -0.0001

Data Index: 544230 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.9542. Min Act: -0.0001

Data Index: 1331925 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.9614. Min Act: -0.0001

Data Index: 667660 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.7977. Min Act: -0.0001

Data Index: 350945 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.9755. Min Act: -0.0001

Data Index: 32945 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.8044. Min Act: -0.0001

Data Index: 145469 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.7670. Min Act: -0.0001

Data Index: 875856 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.7707. Min Act: -0.0001

Data Index: 1035571 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.7767. Min Act: -0.0001

Data Index: 933528 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.7692. Min Act: -0.0001

Data Index: 185589 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.7313. Min Act: -0.0001

Data Index: 661527 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.7135. Min Act: -0.0001

Data Index: 65281 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.7416. Min Act: -0.0001

Data Index: 980893 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.7207. Min Act: -0.0001

Data Index: 1287893 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.6905. Min Act: -0.0001

Data Index: 1043026 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.6862. Min Act: -0.0001

Data Index: 1290921 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.6761. Min Act: -0.0001

Data Index: 959951 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.6051. Min Act: -0.0001

Data Index: 208785 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 1.1556. Min Range: -1.1556

Max Act: 0.7115. Min Act: -0.0001

Data Index: 1276098 (C4 (Web Text))

Max Activating Token Index: 4