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

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

Neuron 4802 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: 2.0741. Min Range: -2.0741

Max Act: 2.0741. Min Act: -0.0000

Data Index: 1426589 (Python Code)

Max Activating Token Index: 347

Text #1

Max Range: 2.0741. Min Range: -2.0741

Max Act: 1.7885. Min Act: -0.0000

Data Index: 328972 (C4 (Web Text))

Max Activating Token Index: 116

Text #2

Max Range: 2.0741. Min Range: -2.0741

Max Act: 1.6745. Min Act: -0.0000

Data Index: 1635434 (Python Code)

Max Activating Token Index: 24

Text #3

Max Range: 2.0741. Min Range: -2.0741

Max Act: 1.6220. Min Act: -0.0000

Data Index: 1390139 (Python Code)

Max Activating Token Index: 289

Text #4

Max Range: 2.0741. Min Range: -2.0741

Max Act: 1.5556. Min Act: -0.0000

Data Index: 1372616 (Python Code)

Max Activating Token Index: 621

Text #5

Max Range: 2.0741. Min Range: -2.0741

Max Act: 1.5427. Min Act: -0.0000

Data Index: 1441564 (Python Code)

Max Activating Token Index: 351

Text #6

Max Range: 2.0741. Min Range: -2.0741

Max Act: 1.5803. Min Act: -0.0000

Data Index: 1655065 (Python Code)

Max Activating Token Index: 840

Text #7

Max Range: 2.0741. Min Range: -2.0741

Max Act: 1.4961. Min Act: -0.0000

Data Index: 1519736 (Python Code)

Max Activating Token Index: 497

Text #8

Max Range: 2.0741. Min Range: -2.0741

Max Act: 1.4892. Min Act: -0.0000

Data Index: 1468529 (Python Code)

Max Activating Token Index: 295

Text #9

Max Range: 2.0741. Min Range: -2.0741

Max Act: 1.4301. Min Act: -0.0000

Data Index: 1385505 (Python Code)

Max Activating Token Index: 924

Text #10

Max Range: 2.0741. Min Range: -2.0741

Max Act: 1.4625. Min Act: -0.0000

Data Index: 1372161 (Python Code)

Max Activating Token Index: 604

Text #11

Max Range: 2.0741. Min Range: -2.0741

Max Act: 1.4566. Min Act: -0.0000

Data Index: 918317 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 2.0741. Min Range: -2.0741

Max Act: 1.4593. Min Act: -0.0000

Data Index: 1518652 (Python Code)

Max Activating Token Index: 928

Text #13

Max Range: 2.0741. Min Range: -2.0741

Max Act: 1.5043. Min Act: -0.0000

Data Index: 1393107 (Python Code)

Max Activating Token Index: 39

Text #14

Max Range: 2.0741. Min Range: -2.0741

Max Act: 1.4140. Min Act: -0.0000

Data Index: 1392311 (Python Code)

Max Activating Token Index: 308

Text #15

Max Range: 2.0741. Min Range: -2.0741

Max Act: 1.3892. Min Act: -0.0000

Data Index: 1213460 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 2.0741. Min Range: -2.0741

Max Act: 1.3702. Min Act: -0.0000

Data Index: 1592348 (Python Code)

Max Activating Token Index: 675

Text #17

Max Range: 2.0741. Min Range: -2.0741

Max Act: 1.3557. Min Act: -0.0000

Data Index: 1417782 (Python Code)

Max Activating Token Index: 769

Text #18

Max Range: 2.0741. Min Range: -2.0741

Max Act: 1.3471. Min Act: -0.0000

Data Index: 1568429 (Python Code)

Max Activating Token Index: 801

Text #19

Max Range: 2.0741. Min Range: -2.0741

Max Act: 1.3229. Min Act: -0.0000

Data Index: 1564313 (Python Code)

Max Activating Token Index: 1013