Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2483 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1540. Min Act: -0.0001

Data Index: 773228 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1421. Min Act: -0.0001

Data Index: 467392 (C4 (Web Text))

Max Activating Token Index: 687

Text #2

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1381. Min Act: -0.0001

Data Index: 39726 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1428. Min Act: -0.0001

Data Index: 826583 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1322. Min Act: -0.0001

Data Index: 548074 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1348. Min Act: -0.0001

Data Index: 171035 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1401. Min Act: -0.0001

Data Index: 1011854 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1291. Min Act: -0.0001

Data Index: 854151 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1238. Min Act: -0.0001

Data Index: 929403 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1278. Min Act: -0.0001

Data Index: 1228212 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1313. Min Act: -0.0001

Data Index: 520135 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1239. Min Act: -0.0001

Data Index: 483294 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1228. Min Act: -0.0001

Data Index: 466604 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1127. Min Act: -0.0001

Data Index: 984015 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1112. Min Act: -0.0001

Data Index: 529469 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1083. Min Act: -0.0001

Data Index: 57934 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1087436 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1165. Min Act: -0.0001

Data Index: 1031894 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1097. Min Act: -0.0001

Data Index: 277640 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.1540. Min Range: -0.1540

Max Act: 0.1052. Min Act: -0.0001

Data Index: 555835 (C4 (Web Text))

Max Activating Token Index: 757