Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1899 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0793. Min Range: -1.0793

Max Act: 1.0793. Min Act: -0.0004

Data Index: 1585631 (Python Code)

Max Activating Token Index: 21

Text #1

Max Range: 1.0793. Min Range: -1.0793

Max Act: 1.0618. Min Act: -0.0004

Data Index: 169287 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 1.0793. Min Range: -1.0793

Max Act: 1.0265. Min Act: -0.0004

Data Index: 505826 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 1.0793. Min Range: -1.0793

Max Act: 1.0203. Min Act: -0.0004

Data Index: 1090187 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.9749. Min Act: -0.0004

Data Index: 984264 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.9818. Min Act: -0.0004

Data Index: 692469 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.9877. Min Act: -0.0004

Data Index: 1336897 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.9287. Min Act: -0.0004

Data Index: 282242 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.9511. Min Act: -0.0004

Data Index: 803120 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.9778. Min Act: -0.0004

Data Index: 425808 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.9095. Min Act: -0.0004

Data Index: 878222 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.9400. Min Act: -0.0004

Data Index: 1117091 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.8807. Min Act: -0.0004

Data Index: 1141635 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.9394. Min Act: -0.0004

Data Index: 169741 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.9376. Min Act: -0.0004

Data Index: 1015882 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.9296. Min Act: -0.0004

Data Index: 8669 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.9492. Min Act: -0.0004

Data Index: 843117 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.8956. Min Act: -0.0004

Data Index: 1329448 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.8608. Min Act: -0.0004

Data Index: 714136 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 1.0793. Min Range: -1.0793

Max Act: 0.8894. Min Act: -0.0004

Data Index: 164946 (C4 (Web Text))

Max Activating Token Index: 441