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

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

Neuron 1172 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: 0.4484. Min Range: -0.4484

Max Act: 0.4408. Min Act: -0.0001

Data Index: 30069 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.4178. Min Act: -0.0001

Data Index: 1261557 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.4324. Min Act: -0.0001

Data Index: 1015829 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.4401. Min Act: -0.0001

Data Index: 485296 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.4133. Min Act: -0.0001

Data Index: 1329391 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3992. Min Act: -0.0001

Data Index: 949892 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.4220. Min Act: -0.0001

Data Index: 1002915 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.4122. Min Act: -0.0001

Data Index: 1346067 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.4484. Min Act: -0.0001

Data Index: 592587 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.4018. Min Act: -0.0001

Data Index: 72682 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3849. Min Act: -0.0001

Data Index: 1228207 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.4023. Min Act: -0.0001

Data Index: 690891 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3545. Min Act: -0.0001

Data Index: 869583 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3961. Min Act: -0.0001

Data Index: 147621 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3598. Min Act: -0.0001

Data Index: 948041 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.4153. Min Act: -0.0001

Data Index: 1096616 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3654. Min Act: -0.0001

Data Index: 634673 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3625. Min Act: -0.0001

Data Index: 179669 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3554. Min Act: -0.0001

Data Index: 1295466 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 0.4484. Min Range: -0.4484

Max Act: 0.3655. Min Act: -0.0001

Data Index: 163186 (C4 (Web Text))

Max Activating Token Index: 352