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

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

Neuron 1986 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: 0.6747. Min Range: -0.6747

Max Act: 0.6747. Min Act: -0.0000

Data Index: 1274433 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.6383. Min Act: -0.0000

Data Index: 720541 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.6269. Min Act: -0.0000

Data Index: 1131598 (C4 (Web Text))

Max Activating Token Index: 642

Text #3

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5865. Min Act: -0.0000

Data Index: 403341 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5890. Min Act: -0.0000

Data Index: 944072 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5863. Min Act: -0.0000

Data Index: 982226 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5683. Min Act: -0.0000

Data Index: 733507 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5474. Min Act: -0.0000

Data Index: 500451 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5878. Min Act: -0.0000

Data Index: 718186 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5708. Min Act: -0.0000

Data Index: 565911 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5723. Min Act: -0.0000

Data Index: 694344 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5684. Min Act: -0.0000

Data Index: 146337 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5615. Min Act: -0.0000

Data Index: 949731 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5437. Min Act: -0.0000

Data Index: 795503 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5375. Min Act: -0.0000

Data Index: 574372 (C4 (Web Text))

Max Activating Token Index: 116

Text #15

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5860. Min Act: -0.0000

Data Index: 215720 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5502. Min Act: -0.0000

Data Index: 934750 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1164186 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5311. Min Act: -0.0000

Data Index: 232801 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.6747. Min Range: -0.6747

Max Act: 0.5350. Min Act: -0.0000

Data Index: 565406 (C4 (Web Text))

Max Activating Token Index: 966