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

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

Neuron 44 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1594. Min Act: -0.0000

Data Index: 239621 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1351. Min Act: -0.0000

Data Index: 188053 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1413. Min Act: -0.0000

Data Index: 643878 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1332. Min Act: -0.0000

Data Index: 1329854 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1294. Min Act: -0.0000

Data Index: 221402 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1229. Min Act: -0.0000

Data Index: 118299 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1202. Min Act: -0.0000

Data Index: 123924 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1214. Min Act: -0.0000

Data Index: 1386968 (Python Code)

Max Activating Token Index: 828

Text #8

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1112. Min Act: -0.0000

Data Index: 1039848 (C4 (Web Text))

Max Activating Token Index: 510

Text #9

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1193. Min Act: -0.0000

Data Index: 548047 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1110. Min Act: -0.0000

Data Index: 158549 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1452711 (Python Code)

Max Activating Token Index: 419

Text #12

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1103. Min Act: -0.0000

Data Index: 740760 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.0983. Min Act: -0.0000

Data Index: 281019 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1074. Min Act: -0.0000

Data Index: 554362 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1040. Min Act: -0.0000

Data Index: 1339968 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1012. Min Act: -0.0000

Data Index: 736095 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1006. Min Act: -0.0000

Data Index: 1015141 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1126. Min Act: -0.0000

Data Index: 1463460 (Python Code)

Max Activating Token Index: 470

Text #19

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1078. Min Act: -0.0000

Data Index: 114587 (C4 (Web Text))

Max Activating Token Index: 751