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

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

Neuron 472 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0420. Min Act: -0.0004

Data Index: 930190 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0407. Min Act: -0.0004

Data Index: 148707 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0386. Min Act: -0.0004

Data Index: 1619647 (Python Code)

Max Activating Token Index: 319

Text #3

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0333. Min Act: -0.0004

Data Index: 1562838 (Python Code)

Max Activating Token Index: 338

Text #4

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0322. Min Act: -0.0004

Data Index: 1482678 (Python Code)

Max Activating Token Index: 957

Text #5

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0319. Min Act: -0.0004

Data Index: 1410353 (Python Code)

Max Activating Token Index: 758

Text #6

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0334. Min Act: -0.0004

Data Index: 1178714 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0300. Min Act: -0.0004

Data Index: 1582194 (Python Code)

Max Activating Token Index: 463

Text #8

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0303. Min Act: -0.0004

Data Index: 485416 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0284. Min Act: -0.0004

Data Index: 1625451 (Python Code)

Max Activating Token Index: 522

Text #10

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0300. Min Act: -0.0004

Data Index: 1364248 (Python Code)

Max Activating Token Index: 770

Text #11

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0266. Min Act: -0.0004

Data Index: 128275 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0294. Min Act: -0.0004

Data Index: 1382375 (Python Code)

Max Activating Token Index: 317

Text #13

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0265. Min Act: -0.0004

Data Index: 1398399 (Python Code)

Max Activating Token Index: 898

Text #14

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0275. Min Act: -0.0004

Data Index: 1110415 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0272. Min Act: -0.0004

Data Index: 276695 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0268. Min Act: -0.0004

Data Index: 246506 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0274. Min Act: -0.0004

Data Index: 1131623 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0273. Min Act: -0.0004

Data Index: 25025 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0267. Min Act: -0.0004

Data Index: 1588686 (Python Code)

Max Activating Token Index: 326