Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 567 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6454. Min Range: -0.6454

Max Act: 0.6290. Min Act: -0.0001

Data Index: 1208338 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.6454. Min Range: -0.6454

Max Act: 0.6454. Min Act: -0.0001

Data Index: 934178 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.6454. Min Range: -0.6454

Max Act: 0.5520. Min Act: -0.0000

Data Index: 403822 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 0.6454. Min Range: -0.6454

Max Act: 0.5857. Min Act: -0.0001

Data Index: 167825 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.6454. Min Range: -0.6454

Max Act: 0.5750. Min Act: -0.0000

Data Index: 171166 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 0.6454. Min Range: -0.6454

Max Act: 0.5517. Min Act: -0.0001

Data Index: 1093134 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 0.6454. Min Range: -0.6454

Max Act: 0.4747. Min Act: -0.0000

Data Index: 823349 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.6454. Min Range: -0.6454

Max Act: 0.4849. Min Act: -0.0001

Data Index: 351734 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 0.6454. Min Range: -0.6454

Max Act: 0.4241. Min Act: -0.0000

Data Index: 1163418 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.6454. Min Range: -0.6454

Max Act: 0.4557. Min Act: -0.0001

Data Index: 1167003 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.6454. Min Range: -0.6454

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1186708 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 0.6454. Min Range: -0.6454

Max Act: 0.4129. Min Act: -0.0001

Data Index: 957355 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.6454. Min Range: -0.6454

Max Act: 0.4007. Min Act: -0.0000

Data Index: 302738 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.6454. Min Range: -0.6454

Max Act: 0.4180. Min Act: -0.0000

Data Index: 439403 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 0.6454. Min Range: -0.6454

Max Act: 0.3753. Min Act: -0.0000

Data Index: 1229609 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 0.6454. Min Range: -0.6454

Max Act: 0.3756. Min Act: -0.0000

Data Index: 755580 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 0.6454. Min Range: -0.6454

Max Act: 0.3736. Min Act: -0.0001

Data Index: 264465 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.6454. Min Range: -0.6454

Max Act: 0.3760. Min Act: -0.0000

Data Index: 987827 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 0.6454. Min Range: -0.6454

Max Act: 0.3737. Min Act: -0.0001

Data Index: 705099 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.6454. Min Range: -0.6454

Max Act: 0.3913. Min Act: -0.0001

Data Index: 365175 (C4 (Web Text))

Max Activating Token Index: 659