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

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

Neuron 3382 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: 0.4063. Min Range: -0.4063

Max Act: 0.3974. Min Act: -0.0001

Data Index: 158142 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.4063. Min Act: -0.0001

Data Index: 558920 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3978. Min Act: -0.0001

Data Index: 559823 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3802. Min Act: -0.0001

Data Index: 585032 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3750. Min Act: -0.0001

Data Index: 1289508 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3630. Min Act: -0.0001

Data Index: 1221574 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3634. Min Act: -0.0001

Data Index: 1288210 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3330. Min Act: -0.0001

Data Index: 84349 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3924. Min Act: -0.0001

Data Index: 555235 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3580. Min Act: -0.0001

Data Index: 1044826 (C4 (Web Text))

Max Activating Token Index: 343

Text #10

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3666. Min Act: -0.0001

Data Index: 838331 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3609. Min Act: -0.0001

Data Index: 503632 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3500. Min Act: -0.0001

Data Index: 359931 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3453. Min Act: -0.0001

Data Index: 1172527 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3353. Min Act: -0.0001

Data Index: 232845 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3571. Min Act: -0.0001

Data Index: 1075772 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3295. Min Act: -0.0001

Data Index: 500721 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3727. Min Act: -0.0001

Data Index: 752344 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3483. Min Act: -0.0001

Data Index: 513665 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.3580. Min Act: -0.0001

Data Index: 372301 (C4 (Web Text))

Max Activating Token Index: 240