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

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

Neuron 5124 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.5497. Min Act: -0.0000

Data Index: 634757 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.4182. Min Act: -0.0000

Data Index: 1651015 (Python Code)

Max Activating Token Index: 978

Text #2

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3830. Min Act: -0.0000

Data Index: 1585833 (Python Code)

Max Activating Token Index: 759

Text #3

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3621. Min Act: -0.0000

Data Index: 1408667 (Python Code)

Max Activating Token Index: 899

Text #4

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3526. Min Act: -0.0000

Data Index: 1482699 (Python Code)

Max Activating Token Index: 689

Text #5

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3630. Min Act: -0.0000

Data Index: 1205958 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3575. Min Act: -0.0000

Data Index: 1251139 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3433. Min Act: -0.0000

Data Index: 1410416 (Python Code)

Max Activating Token Index: 889

Text #8

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3508. Min Act: -0.0000

Data Index: 1516383 (Python Code)

Max Activating Token Index: 986

Text #9

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3527. Min Act: -0.0000

Data Index: 1528908 (Python Code)

Max Activating Token Index: 653

Text #10

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3490. Min Act: -0.0000

Data Index: 1401066 (Python Code)

Max Activating Token Index: 579

Text #11

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3895. Min Act: -0.0000

Data Index: 1455565 (Python Code)

Max Activating Token Index: 331

Text #12

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1518754 (Python Code)

Max Activating Token Index: 653

Text #13

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3438. Min Act: -0.0000

Data Index: 1649296 (Python Code)

Max Activating Token Index: 510

Text #14

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3407. Min Act: -0.0000

Data Index: 1411343 (Python Code)

Max Activating Token Index: 1011

Text #15

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1505169 (Python Code)

Max Activating Token Index: 900

Text #16

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3572. Min Act: -0.0000

Data Index: 183708 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3548. Min Act: -0.0000

Data Index: 1544268 (Python Code)

Max Activating Token Index: 706

Text #18

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3355. Min Act: -0.0000

Data Index: 1585627 (Python Code)

Max Activating Token Index: 850

Text #19

Max Range: 0.5497. Min Range: -0.5497

Max Act: 0.3203. Min Act: -0.0000

Data Index: 1539148 (Python Code)

Max Activating Token Index: 815