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

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

Neuron 439 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0348. Min Act: -0.0000

Data Index: 1268836 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0370. Min Act: -0.0000

Data Index: 679484 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0322. Min Act: -0.0000

Data Index: 551972 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0348. Min Act: -0.0000

Data Index: 475308 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0318. Min Act: -0.0000

Data Index: 414181 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0290. Min Act: -0.0000

Data Index: 492996 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0330. Min Act: -0.0000

Data Index: 1401435 (Python Code)

Max Activating Token Index: 310

Text #7

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0342. Min Act: -0.0000

Data Index: 809661 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0313. Min Act: -0.0000

Data Index: 463694 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0310. Min Act: -0.0000

Data Index: 490134 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0290. Min Act: -0.0000

Data Index: 716586 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0279. Min Act: -0.0000

Data Index: 961421 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0345. Min Act: -0.0000

Data Index: 268849 (C4 (Web Text))

Max Activating Token Index: 861

Text #13

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0279. Min Act: -0.0000

Data Index: 1594191 (Python Code)

Max Activating Token Index: 273

Text #14

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0279. Min Act: -0.0000

Data Index: 1363158 (Python Code)

Max Activating Token Index: 599

Text #15

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0275. Min Act: -0.0000

Data Index: 1304303 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0267. Min Act: -0.0000

Data Index: 1045994 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0208. Min Act: -0.0000

Data Index: 807045 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0261. Min Act: -0.0000

Data Index: 1471968 (Python Code)

Max Activating Token Index: 843

Text #19

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0259. Min Act: -0.0000

Data Index: 1414172 (Python Code)

Max Activating Token Index: 142