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

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

Neuron 1214 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9053. Min Range: -0.9053

Max Act: 0.9053. Min Act: 0.0000

Data Index: 1527671 (Python Code)

Max Activating Token Index: 422

Text #1

Max Range: 0.9053. Min Range: -0.9053

Max Act: 0.8479. Min Act: 0.0000

Data Index: 1390750 (Python Code)

Max Activating Token Index: 908

Text #2

Max Range: 0.9053. Min Range: -0.9053

Max Act: 0.7666. Min Act: 0.0000

Data Index: 1650938 (Python Code)

Max Activating Token Index: 670

Text #3

Max Range: 0.9053. Min Range: -0.9053

Max Act: 0.5825. Min Act: 0.0000

Data Index: 1497329 (Python Code)

Max Activating Token Index: 822

Text #4

Max Range: 0.9053. Min Range: -0.9053

Max Act: 0.6436. Min Act: 0.0001

Data Index: 1380469 (Python Code)

Max Activating Token Index: 432

Text #5

Max Range: 0.9053. Min Range: -0.9053

Max Act: 0.6928. Min Act: 0.0000

Data Index: 1401320 (Python Code)

Max Activating Token Index: 864

Text #6

Max Range: 0.9053. Min Range: -0.9053

Max Act: 0.5769. Min Act: 0.0001

Data Index: 1383157 (Python Code)

Max Activating Token Index: 470

Text #7

Max Range: 0.9053. Min Range: -0.9053

Max Act: 0.6518. Min Act: 0.0000

Data Index: 1626217 (Python Code)

Max Activating Token Index: 468

Text #8

Max Range: 0.9053. Min Range: -0.9053

Max Act: 0.5684. Min Act: 0.0001

Data Index: 1621276 (Python Code)

Max Activating Token Index: 460

Text #9

Max Range: 0.9053. Min Range: -0.9053

Max Act: 0.4952. Min Act: 0.0001

Data Index: 1515840 (Python Code)

Max Activating Token Index: 298

Text #10

Max Range: 0.9053. Min Range: -0.9053

Max Act: 0.5037. Min Act: 0.0001

Data Index: 1531354 (Python Code)

Max Activating Token Index: 537

Text #11

Max Range: 0.9053. Min Range: -0.9053

Max Act: 0.5756. Min Act: 0.0001

Data Index: 1581218 (Python Code)

Max Activating Token Index: 244

Text #12

Max Range: 0.9053. Min Range: -0.9053

Max Act: 0.5776. Min Act: -0.0000

Data Index: 1548653 (Python Code)

Max Activating Token Index: 88

Text #13

Max Range: 0.9053. Min Range: -0.9053

Max Act: 0.4486. Min Act: -0.0000

Data Index: 1511511 (Python Code)

Max Activating Token Index: 177

Text #14

Max Range: 0.9053. Min Range: -0.9053

Max Act: 0.4928. Min Act: 0.0000

Data Index: 1430545 (Python Code)

Max Activating Token Index: 528

Text #15

Max Range: 0.9053. Min Range: -0.9053

Max Act: 0.4542. Min Act: 0.0001

Data Index: 1536121 (Python Code)

Max Activating Token Index: 534

Text #16

Max Range: 0.9053. Min Range: -0.9053

Max Act: 0.4720. Min Act: -0.0000

Data Index: 1589237 (Python Code)

Max Activating Token Index: 521

Text #17

Max Range: 0.9053. Min Range: -0.9053

Max Act: 0.4291. Min Act: 0.0001

Data Index: 1446785 (Python Code)

Max Activating Token Index: 150

Text #18

Max Range: 0.9053. Min Range: -0.9053

Max Act: 0.4847. Min Act: 0.0001

Data Index: 1582642 (Python Code)

Max Activating Token Index: 974

Text #19

Max Range: 0.9053. Min Range: -0.9053

Max Act: 0.4301. Min Act: 0.0000

Data Index: 1642618 (Python Code)

Max Activating Token Index: 369