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

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

Neuron 2414 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: 0.1432. Min Range: -0.1432

Max Act: 0.1405. Min Act: -0.0001

Data Index: 900532 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1432. Min Act: -0.0001

Data Index: 1369201 (Python Code)

Max Activating Token Index: 442

Text #2

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1362. Min Act: -0.0001

Data Index: 1116802 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1375. Min Act: -0.0001

Data Index: 1393802 (Python Code)

Max Activating Token Index: 377

Text #4

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1267. Min Act: -0.0001

Data Index: 1461414 (Python Code)

Max Activating Token Index: 464

Text #5

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1326. Min Act: -0.0001

Data Index: 855513 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1093. Min Act: -0.0001

Data Index: 436989 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1100. Min Act: -0.0001

Data Index: 1648845 (Python Code)

Max Activating Token Index: 269

Text #8

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1180. Min Act: -0.0001

Data Index: 578279 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1035. Min Act: -0.0001

Data Index: 1460614 (Python Code)

Max Activating Token Index: 353

Text #10

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1046. Min Act: -0.0001

Data Index: 1490898 (Python Code)

Max Activating Token Index: 689

Text #11

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1164. Min Act: -0.0001

Data Index: 218339 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1200. Min Act: -0.0001

Data Index: 383054 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1108. Min Act: -0.0001

Data Index: 285697 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1233. Min Act: -0.0001

Data Index: 548322 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1189. Min Act: -0.0001

Data Index: 1638703 (Python Code)

Max Activating Token Index: 892

Text #16

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1058. Min Act: -0.0001

Data Index: 406687 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1110. Min Act: -0.0001

Data Index: 1291792 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.1050. Min Act: -0.0001

Data Index: 883589 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.1432. Min Range: -0.1432

Max Act: 0.0940. Min Act: -0.0001

Data Index: 1453668 (Python Code)

Max Activating Token Index: 566