Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1516 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0633. Min Act: -0.0002

Data Index: 846249 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0664. Min Act: -0.0002

Data Index: 989998 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0630. Min Act: -0.0001

Data Index: 701082 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1165266 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0572. Min Act: -0.0002

Data Index: 916231 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0579. Min Act: -0.0002

Data Index: 845448 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0578. Min Act: -0.0000

Data Index: 427777 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0561. Min Act: -0.0002

Data Index: 321436 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0583. Min Act: -0.0001

Data Index: 1119995 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0558. Min Act: -0.0001

Data Index: 105969 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0523. Min Act: -0.0002

Data Index: 814447 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0552. Min Act: -0.0002

Data Index: 392664 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0552. Min Act: -0.0002

Data Index: 118363 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0578. Min Act: -0.0001

Data Index: 1140648 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1088744 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0580. Min Act: -0.0000

Data Index: 1162731 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0553. Min Act: -0.0002

Data Index: 952519 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0564. Min Act: -0.0002

Data Index: 46056 (C4 (Web Text))

Max Activating Token Index: 821

Text #18

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0529. Min Act: -0.0002

Data Index: 1000423 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0528. Min Act: -0.0001

Data Index: 774168 (C4 (Web Text))

Max Activating Token Index: 613