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

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

Neuron 4331 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4902. Min Act: -0.0001

Data Index: 55986 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4801. Min Act: -0.0000

Data Index: 157734 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4544. Min Act: -0.0001

Data Index: 190326 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4360. Min Act: -0.0001

Data Index: 97419 (C4 (Web Text))

Max Activating Token Index: 523

Text #4

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4559. Min Act: -0.0001

Data Index: 289841 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4261. Min Act: -0.0001

Data Index: 1584566 (Python Code)

Max Activating Token Index: 781

Text #6

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4153. Min Act: -0.0001

Data Index: 588273 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3672. Min Act: -0.0001

Data Index: 152112 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3784. Min Act: -0.0001

Data Index: 1332504 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4151. Min Act: -0.0001

Data Index: 788271 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3861. Min Act: -0.0001

Data Index: 1302697 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3675. Min Act: -0.0001

Data Index: 293672 (C4 (Web Text))

Max Activating Token Index: 788

Text #12

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3551. Min Act: -0.0001

Data Index: 147852 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3513. Min Act: -0.0001

Data Index: 1008509 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3735. Min Act: -0.0001

Data Index: 804451 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3493. Min Act: -0.0001

Data Index: 582447 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3581. Min Act: -0.0001

Data Index: 203098 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3571. Min Act: -0.0001

Data Index: 848656 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3580. Min Act: -0.0000

Data Index: 1020503 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3747. Min Act: -0.0001

Data Index: 244111 (C4 (Web Text))

Max Activating Token Index: 622