Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4181 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2892. Min Range: -1.2892

Max Act: 1.2892. Min Act: -0.0000

Data Index: 637093 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.8741. Min Act: -0.0000

Data Index: 1443366 (Python Code)

Max Activating Token Index: 888

Text #2

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.6750. Min Act: -0.0000

Data Index: 778112 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.8045. Min Act: 0.0000

Data Index: 1633507 (Python Code)

Max Activating Token Index: 303

Text #4

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.7167. Min Act: -0.0000

Data Index: 1501503 (Python Code)

Max Activating Token Index: 848

Text #5

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.6742. Min Act: -0.0000

Data Index: 585113 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.6739. Min Act: -0.0000

Data Index: 1648602 (Python Code)

Max Activating Token Index: 930

Text #7

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.6945. Min Act: -0.0000

Data Index: 1634040 (Python Code)

Max Activating Token Index: 343

Text #8

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.6946. Min Act: -0.0000

Data Index: 631353 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.7135. Min Act: 0.0001

Data Index: 658847 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.7148. Min Act: -0.0000

Data Index: 79369 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.6817. Min Act: -0.0000

Data Index: 252449 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.6448. Min Act: -0.0000

Data Index: 6789 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.6774. Min Act: -0.0000

Data Index: 1388715 (Python Code)

Max Activating Token Index: 848

Text #14

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.6917. Min Act: -0.0000

Data Index: 1438675 (Python Code)

Max Activating Token Index: 254

Text #15

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.6542. Min Act: -0.0000

Data Index: 246581 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.6078. Min Act: -0.0000

Data Index: 266298 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1390246 (Python Code)

Max Activating Token Index: 296

Text #18

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.5985. Min Act: 0.0002

Data Index: 1119876 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 1.2892. Min Range: -1.2892

Max Act: 0.6281. Min Act: 0.0003

Data Index: 715998 (C4 (Web Text))

Max Activating Token Index: 199