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

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

Neuron 3792 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.4785. Min Act: -0.0001

Data Index: 1479143 (Python Code)

Max Activating Token Index: 755

Text #1

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.4478. Min Act: -0.0000

Data Index: 1596382 (Python Code)

Max Activating Token Index: 18

Text #2

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1417308 (Python Code)

Max Activating Token Index: 43

Text #3

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3545. Min Act: -0.0001

Data Index: 1630444 (Python Code)

Max Activating Token Index: 416

Text #4

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3574. Min Act: -0.0001

Data Index: 1426455 (Python Code)

Max Activating Token Index: 451

Text #5

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3249. Min Act: -0.0001

Data Index: 1513266 (Python Code)

Max Activating Token Index: 702

Text #6

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3495. Min Act: -0.0000

Data Index: 585408 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3432. Min Act: -0.0001

Data Index: 1399900 (Python Code)

Max Activating Token Index: 464

Text #8

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3168. Min Act: -0.0001

Data Index: 1496764 (Python Code)

Max Activating Token Index: 995

Text #9

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.3056. Min Act: -0.0001

Data Index: 1601267 (Python Code)

Max Activating Token Index: 853

Text #10

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.2822. Min Act: -0.0001

Data Index: 1501162 (Python Code)

Max Activating Token Index: 274

Text #11

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.2969. Min Act: -0.0001

Data Index: 1530371 (Python Code)

Max Activating Token Index: 825

Text #12

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.2861. Min Act: -0.0000

Data Index: 1467202 (Python Code)

Max Activating Token Index: 90

Text #13

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1429702 (Python Code)

Max Activating Token Index: 688

Text #14

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.2676. Min Act: -0.0000

Data Index: 1374227 (Python Code)

Max Activating Token Index: 25

Text #15

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.2591. Min Act: -0.0000

Data Index: 909299 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.2591. Min Act: -0.0000

Data Index: 1647083 (Python Code)

Max Activating Token Index: 350

Text #17

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.2571. Min Act: -0.0000

Data Index: 1521962 (Python Code)

Max Activating Token Index: 131

Text #18

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.2568. Min Act: -0.0000

Data Index: 1137841 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 0.4785. Min Range: -0.4785

Max Act: 0.2652. Min Act: -0.0000

Data Index: 1644374 (Python Code)

Max Activating Token Index: 128