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

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

Neuron 171 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4176. Min Range: -2.4176

Max Act: 2.1994. Min Act: -0.0000

Data Index: 449041 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 2.4176. Min Range: -2.4176

Max Act: 2.4176. Min Act: -0.0000

Data Index: 440485 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 2.4176. Min Range: -2.4176

Max Act: 2.2523. Min Act: -0.0000

Data Index: 1193291 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 2.4176. Min Range: -2.4176

Max Act: 1.7007. Min Act: -0.0000

Data Index: 1113626 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 2.4176. Min Range: -2.4176

Max Act: 1.8371. Min Act: -0.0000

Data Index: 1544259 (Python Code)

Max Activating Token Index: 510

Text #5

Max Range: 2.4176. Min Range: -2.4176

Max Act: 1.8084. Min Act: -0.0000

Data Index: 1391390 (Python Code)

Max Activating Token Index: 275

Text #6

Max Range: 2.4176. Min Range: -2.4176

Max Act: 1.8026. Min Act: -0.0000

Data Index: 1440468 (Python Code)

Max Activating Token Index: 641

Text #7

Max Range: 2.4176. Min Range: -2.4176

Max Act: 1.8290. Min Act: -0.0000

Data Index: 1439754 (Python Code)

Max Activating Token Index: 345

Text #8

Max Range: 2.4176. Min Range: -2.4176

Max Act: 1.8444. Min Act: -0.0000

Data Index: 1616714 (Python Code)

Max Activating Token Index: 424

Text #9

Max Range: 2.4176. Min Range: -2.4176

Max Act: 1.7894. Min Act: -0.0000

Data Index: 1369972 (Python Code)

Max Activating Token Index: 710

Text #10

Max Range: 2.4176. Min Range: -2.4176

Max Act: 1.7139. Min Act: -0.0000

Data Index: 641822 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 2.4176. Min Range: -2.4176

Max Act: 1.6570. Min Act: -0.0000

Data Index: 1472334 (Python Code)

Max Activating Token Index: 428

Text #12

Max Range: 2.4176. Min Range: -2.4176

Max Act: 1.7407. Min Act: -0.0000

Data Index: 1497260 (Python Code)

Max Activating Token Index: 494

Text #13

Max Range: 2.4176. Min Range: -2.4176

Max Act: 1.6017. Min Act: -0.0000

Data Index: 1389604 (Python Code)

Max Activating Token Index: 778

Text #14

Max Range: 2.4176. Min Range: -2.4176

Max Act: 1.7085. Min Act: -0.0000

Data Index: 1457017 (Python Code)

Max Activating Token Index: 503

Text #15

Max Range: 2.4176. Min Range: -2.4176

Max Act: 1.6434. Min Act: -0.0000

Data Index: 1475117 (Python Code)

Max Activating Token Index: 320

Text #16

Max Range: 2.4176. Min Range: -2.4176

Max Act: 1.5402. Min Act: -0.0000

Data Index: 1596194 (Python Code)

Max Activating Token Index: 291

Text #17

Max Range: 2.4176. Min Range: -2.4176

Max Act: 1.6772. Min Act: -0.0000

Data Index: 1458239 (Python Code)

Max Activating Token Index: 868

Text #18

Max Range: 2.4176. Min Range: -2.4176

Max Act: 1.6745. Min Act: -0.0000

Data Index: 1489802 (Python Code)

Max Activating Token Index: 307

Text #19

Max Range: 2.4176. Min Range: -2.4176

Max Act: 1.7222. Min Act: -0.0000

Data Index: 1651302 (Python Code)

Max Activating Token Index: 414