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

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

Neuron 3354 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: 0.1474. Min Range: -0.1474

Max Act: 0.1434. Min Act: -0.0000

Data Index: 671759 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1080. Min Act: -0.0000

Data Index: 416843 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1474. Min Act: -0.0000

Data Index: 239485 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1142. Min Act: -0.0000

Data Index: 497282 (C4 (Web Text))

Max Activating Token Index: 1012

Text #4

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1179. Min Act: -0.0000

Data Index: 716560 (C4 (Web Text))

Max Activating Token Index: 631

Text #5

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1217. Min Act: -0.0000

Data Index: 1479462 (Python Code)

Max Activating Token Index: 799

Text #6

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1226. Min Act: -0.0000

Data Index: 1257352 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1195. Min Act: -0.0000

Data Index: 630996 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1253. Min Act: -0.0000

Data Index: 351100 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1125. Min Act: -0.0000

Data Index: 1629325 (Python Code)

Max Activating Token Index: 820

Text #10

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1109. Min Act: -0.0000

Data Index: 1547204 (Python Code)

Max Activating Token Index: 111

Text #11

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1166. Min Act: -0.0000

Data Index: 1443896 (Python Code)

Max Activating Token Index: 328

Text #12

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1109. Min Act: -0.0000

Data Index: 310556 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.0813. Min Act: -0.0000

Data Index: 542707 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1007. Min Act: -0.0000

Data Index: 313352 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1036025 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1078. Min Act: -0.0000

Data Index: 1388486 (Python Code)

Max Activating Token Index: 513

Text #17

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1117. Min Act: -0.0000

Data Index: 1383144 (Python Code)

Max Activating Token Index: 284

Text #18

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1080. Min Act: -0.0000

Data Index: 55727 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1551279 (Python Code)

Max Activating Token Index: 428