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

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

Neuron 5003 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.5829. Min Act: -0.0000

Data Index: 305365 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.5906. Min Act: -0.0000

Data Index: 1153950 (C4 (Web Text))

Max Activating Token Index: 446

Text #2

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.5534. Min Act: -0.0000

Data Index: 1200527 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1358599 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.5200. Min Act: -0.0000

Data Index: 962988 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.5580. Min Act: -0.0000

Data Index: 44122 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4915. Min Act: -0.0000

Data Index: 860621 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4903. Min Act: -0.0000

Data Index: 88695 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.5194. Min Act: -0.0000

Data Index: 56697 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4837. Min Act: -0.0000

Data Index: 515457 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4637. Min Act: -0.0000

Data Index: 757318 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4553. Min Act: -0.0000

Data Index: 1207440 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4683. Min Act: -0.0000

Data Index: 713834 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4634. Min Act: -0.0000

Data Index: 258113 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4653. Min Act: -0.0000

Data Index: 278973 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4472. Min Act: -0.0000

Data Index: 643374 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4435. Min Act: -0.0000

Data Index: 968603 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4297. Min Act: -0.0000

Data Index: 1264614 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4407. Min Act: -0.0000

Data Index: 611482 (C4 (Web Text))

Max Activating Token Index: 673

Text #19

Max Range: 0.5906. Min Range: -0.5906

Max Act: 0.4247. Min Act: -0.0000

Data Index: 309350 (C4 (Web Text))

Max Activating Token Index: 246