Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1386 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3351. Min Range: -2.3351

Max Act: 2.3351. Min Act: -0.0000

Data Index: 419467 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 2.3351. Min Range: -2.3351

Max Act: 2.2684. Min Act: -0.0000

Data Index: 795373 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 2.3351. Min Range: -2.3351

Max Act: 2.1985. Min Act: -0.0000

Data Index: 364247 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 2.3351. Min Range: -2.3351

Max Act: 2.0322. Min Act: -0.0000

Data Index: 475071 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.8549. Min Act: -0.0000

Data Index: 873351 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.8539. Min Act: -0.0000

Data Index: 1089416 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.8316. Min Act: -0.0000

Data Index: 1582184 (Python Code)

Max Activating Token Index: 488

Text #7

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.8668. Min Act: -0.0000

Data Index: 336970 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.8239. Min Act: -0.0000

Data Index: 275260 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.7144. Min Act: -0.0001

Data Index: 1556489 (Python Code)

Max Activating Token Index: 372

Text #10

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.7116. Min Act: -0.0000

Data Index: 1259649 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.6719. Min Act: -0.0000

Data Index: 1566233 (Python Code)

Max Activating Token Index: 336

Text #12

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.7231. Min Act: -0.0000

Data Index: 665462 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.6675. Min Act: -0.0000

Data Index: 652291 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.7160. Min Act: -0.0001

Data Index: 1534744 (Python Code)

Max Activating Token Index: 338

Text #15

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.7602. Min Act: -0.0000

Data Index: 896096 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.6642. Min Act: -0.0000

Data Index: 1616134 (Python Code)

Max Activating Token Index: 448

Text #17

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.6098. Min Act: -0.0000

Data Index: 179897 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.6554. Min Act: -0.0000

Data Index: 1620047 (Python Code)

Max Activating Token Index: 248

Text #19

Max Range: 2.3351. Min Range: -2.3351

Max Act: 1.5811. Min Act: -0.0000

Data Index: 1613521 (Python Code)

Max Activating Token Index: 370