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

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

Neuron 4362 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0541. Min Act: -0.0002

Data Index: 28276 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1177908 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0495. Min Act: -0.0002

Data Index: 278981 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0458. Min Act: -0.0002

Data Index: 862486 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0490. Min Act: -0.0002

Data Index: 690476 (C4 (Web Text))

Max Activating Token Index: 747

Text #5

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1256886 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1341552 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0392. Min Act: -0.0002

Data Index: 630079 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0479. Min Act: -0.0002

Data Index: 1271150 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0344. Min Act: -0.0002

Data Index: 748388 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1286998 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0430. Min Act: -0.0002

Data Index: 259780 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0430. Min Act: -0.0002

Data Index: 19845 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0355. Min Act: -0.0002

Data Index: 373452 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0400. Min Act: -0.0002

Data Index: 1140016 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0264. Min Act: -0.0002

Data Index: 344400 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0395. Min Act: -0.0002

Data Index: 517150 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0419. Min Act: -0.0002

Data Index: 224224 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0393. Min Act: -0.0002

Data Index: 739123 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 0.0581. Min Range: -0.0581

Max Act: 0.0373. Min Act: -0.0002

Data Index: 282607 (C4 (Web Text))

Max Activating Token Index: 443