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

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

Neuron 1635 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.4409. Min Act: -0.0001

Data Index: 955775 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.4214. Min Act: -0.0001

Data Index: 827169 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.4444. Min Act: -0.0001

Data Index: 1021390 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.4346. Min Act: -0.0001

Data Index: 345453 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.4327. Min Act: -0.0001

Data Index: 699635 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.4132. Min Act: -0.0001

Data Index: 1195725 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.4081. Min Act: -0.0001

Data Index: 389346 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.4381. Min Act: -0.0001

Data Index: 158256 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.4103. Min Act: -0.0001

Data Index: 977175 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.4265. Min Act: -0.0001

Data Index: 812368 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.4114. Min Act: -0.0001

Data Index: 362713 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.4205. Min Act: -0.0001

Data Index: 862815 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3870. Min Act: -0.0001

Data Index: 100574 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3866. Min Act: -0.0001

Data Index: 567788 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3970. Min Act: -0.0001

Data Index: 37009 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3763. Min Act: -0.0001

Data Index: 702810 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.4019. Min Act: -0.0001

Data Index: 1337891 (C4 (Web Text))

Max Activating Token Index: 232

Text #17

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.4139. Min Act: -0.0001

Data Index: 891787 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3725. Min Act: -0.0001

Data Index: 1042870 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.4444. Min Range: -0.4444

Max Act: 0.3935. Min Act: -0.0001

Data Index: 376941 (C4 (Web Text))

Max Activating Token Index: 71