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

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

Neuron 2435 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1860. Min Act: -0.0003

Data Index: 604825 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1579. Min Act: -0.0003

Data Index: 97008 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1689. Min Act: -0.0003

Data Index: 62273 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1387. Min Act: -0.0003

Data Index: 236440 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1591. Min Act: -0.0003

Data Index: 822407 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1580. Min Act: -0.0003

Data Index: 91018 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1549. Min Act: -0.0003

Data Index: 136317 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1403. Min Act: -0.0003

Data Index: 623667 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1479. Min Act: -0.0003

Data Index: 557152 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1386. Min Act: -0.0003

Data Index: 317774 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1504. Min Act: -0.0003

Data Index: 1333820 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1220. Min Act: -0.0003

Data Index: 312986 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1601. Min Act: -0.0003

Data Index: 1310715 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1337. Min Act: -0.0003

Data Index: 1215552 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1414. Min Act: -0.0003

Data Index: 44346 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1452. Min Act: -0.0003

Data Index: 305508 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1221. Min Act: -0.0003

Data Index: 997428 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1191. Min Act: -0.0003

Data Index: 130131 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1225. Min Act: -0.0003

Data Index: 22494 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1227. Min Act: -0.0003

Data Index: 1263449 (C4 (Web Text))

Max Activating Token Index: 951