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

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

Neuron 1567 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: 0.9640. Min Range: -0.9640

Max Act: 0.9365. Min Act: -0.0001

Data Index: 961829 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.9640. Min Act: -0.0001

Data Index: 897183 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.8718. Min Act: -0.0001

Data Index: 1344030 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.8774. Min Act: -0.0001

Data Index: 900308 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.7629. Min Act: -0.0001

Data Index: 1230581 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.7590. Min Act: -0.0001

Data Index: 313982 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.8140. Min Act: -0.0001

Data Index: 746370 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.7316. Min Act: -0.0001

Data Index: 510263 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.8089. Min Act: -0.0001

Data Index: 324990 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.7838. Min Act: -0.0001

Data Index: 1197491 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.7229. Min Act: -0.0001

Data Index: 879682 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6804. Min Act: -0.0001

Data Index: 946468 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.7785. Min Act: -0.0001

Data Index: 706913 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.7186. Min Act: -0.0001

Data Index: 1054032 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.7145. Min Act: -0.0001

Data Index: 1280195 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6980. Min Act: -0.0001

Data Index: 1310721 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6422. Min Act: -0.0001

Data Index: 36550 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6458. Min Act: -0.0001

Data Index: 221486 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.7686. Min Act: -0.0001

Data Index: 250304 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.9640. Min Range: -0.9640

Max Act: 0.6716. Min Act: -0.0001

Data Index: 932087 (C4 (Web Text))

Max Activating Token Index: 574