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

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

Neuron 10 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: 2.3218. Min Range: -2.3218

Max Act: 2.3218. Min Act: -0.0000

Data Index: 1512330 (Python Code)

Max Activating Token Index: 463

Text #1

Max Range: 2.3218. Min Range: -2.3218

Max Act: 2.0618. Min Act: -0.0000

Data Index: 1604935 (Python Code)

Max Activating Token Index: 335

Text #2

Max Range: 2.3218. Min Range: -2.3218

Max Act: 2.1796. Min Act: -0.0000

Data Index: 1373852 (Python Code)

Max Activating Token Index: 620

Text #3

Max Range: 2.3218. Min Range: -2.3218

Max Act: 2.0442. Min Act: -0.0000

Data Index: 1538157 (Python Code)

Max Activating Token Index: 451

Text #4

Max Range: 2.3218. Min Range: -2.3218

Max Act: 2.0988. Min Act: -0.0000

Data Index: 1507235 (Python Code)

Max Activating Token Index: 474

Text #5

Max Range: 2.3218. Min Range: -2.3218

Max Act: 1.9442. Min Act: 0.0001

Data Index: 1646570 (Python Code)

Max Activating Token Index: 802

Text #6

Max Range: 2.3218. Min Range: -2.3218

Max Act: 2.0460. Min Act: 0.0000

Data Index: 1374598 (Python Code)

Max Activating Token Index: 190

Text #7

Max Range: 2.3218. Min Range: -2.3218

Max Act: 2.0247. Min Act: -0.0000

Data Index: 1381170 (Python Code)

Max Activating Token Index: 908

Text #8

Max Range: 2.3218. Min Range: -2.3218

Max Act: 1.9774. Min Act: -0.0000

Data Index: 1551810 (Python Code)

Max Activating Token Index: 49

Text #9

Max Range: 2.3218. Min Range: -2.3218

Max Act: 1.9704. Min Act: -0.0000

Data Index: 1453125 (Python Code)

Max Activating Token Index: 534

Text #10

Max Range: 2.3218. Min Range: -2.3218

Max Act: 1.9099. Min Act: -0.0000

Data Index: 1617285 (Python Code)

Max Activating Token Index: 477

Text #11

Max Range: 2.3218. Min Range: -2.3218

Max Act: 1.8713. Min Act: 0.0000

Data Index: 1475614 (Python Code)

Max Activating Token Index: 265

Text #12

Max Range: 2.3218. Min Range: -2.3218

Max Act: 2.0019. Min Act: 0.0000

Data Index: 1646399 (Python Code)

Max Activating Token Index: 933

Text #13

Max Range: 2.3218. Min Range: -2.3218

Max Act: 1.9575. Min Act: -0.0000

Data Index: 1507411 (Python Code)

Max Activating Token Index: 461

Text #14

Max Range: 2.3218. Min Range: -2.3218

Max Act: 1.8273. Min Act: -0.0000

Data Index: 1103667 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 2.3218. Min Range: -2.3218

Max Act: 1.7606. Min Act: -0.0000

Data Index: 1554148 (Python Code)

Max Activating Token Index: 538

Text #16

Max Range: 2.3218. Min Range: -2.3218

Max Act: 1.8674. Min Act: -0.0000

Data Index: 1427490 (Python Code)

Max Activating Token Index: 340

Text #17

Max Range: 2.3218. Min Range: -2.3218

Max Act: 1.7636. Min Act: 0.0000

Data Index: 1593543 (Python Code)

Max Activating Token Index: 126

Text #18

Max Range: 2.3218. Min Range: -2.3218

Max Act: 1.7623. Min Act: -0.0000

Data Index: 1436443 (Python Code)

Max Activating Token Index: 464

Text #19

Max Range: 2.3218. Min Range: -2.3218

Max Act: 1.7364. Min Act: -0.0000

Data Index: 1375200 (Python Code)

Max Activating Token Index: 647