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

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

Neuron 4504 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.6401. Min Act: -0.0000

Data Index: 597979 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.4785. Min Act: -0.0000

Data Index: 208841 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.4417. Min Act: -0.0000

Data Index: 358537 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.4473. Min Act: -0.0000

Data Index: 684751 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.4160. Min Act: -0.0000

Data Index: 460766 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.4157. Min Act: -0.0000

Data Index: 919618 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.4034. Min Act: -0.0000

Data Index: 1289079 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.3779. Min Act: -0.0000

Data Index: 586015 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.3686. Min Act: -0.0000

Data Index: 205972 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.3562. Min Act: -0.0000

Data Index: 1290209 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.3651. Min Act: -0.0000

Data Index: 812097 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.3690. Min Act: -0.0000

Data Index: 341259 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.3426. Min Act: -0.0000

Data Index: 1155290 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.3507. Min Act: -0.0000

Data Index: 1117156 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.3516. Min Act: -0.0000

Data Index: 7905 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.3479. Min Act: -0.0000

Data Index: 937758 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.3466. Min Act: -0.0000

Data Index: 638248 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.3284. Min Act: -0.0000

Data Index: 340681 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.3297. Min Act: -0.0000

Data Index: 648858 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 0.6401. Min Range: -0.6401

Max Act: 0.3250. Min Act: -0.0000

Data Index: 223538 (C4 (Web Text))

Max Activating Token Index: 312