Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1972 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.5950. Min Act: -0.0001

Data Index: 1532280 (Python Code)

Max Activating Token Index: 402

Text #1

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4716. Min Act: -0.0001

Data Index: 1378312 (Python Code)

Max Activating Token Index: 54

Text #2

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4642. Min Act: -0.0001

Data Index: 1571133 (Python Code)

Max Activating Token Index: 863

Text #3

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4649. Min Act: -0.0001

Data Index: 1568486 (Python Code)

Max Activating Token Index: 949

Text #4

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4376. Min Act: -0.0001

Data Index: 1392470 (Python Code)

Max Activating Token Index: 452

Text #5

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4261. Min Act: -0.0001

Data Index: 1401439 (Python Code)

Max Activating Token Index: 751

Text #6

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4433. Min Act: -0.0001

Data Index: 1553527 (Python Code)

Max Activating Token Index: 200

Text #7

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4544. Min Act: -0.0001

Data Index: 1539463 (Python Code)

Max Activating Token Index: 916

Text #8

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4391. Min Act: -0.0001

Data Index: 1381861 (Python Code)

Max Activating Token Index: 1014

Text #9

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4518. Min Act: -0.0001

Data Index: 1417508 (Python Code)

Max Activating Token Index: 1021

Text #10

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4364. Min Act: -0.0001

Data Index: 1515507 (Python Code)

Max Activating Token Index: 166

Text #11

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4330. Min Act: -0.0001

Data Index: 1563809 (Python Code)

Max Activating Token Index: 222

Text #12

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4175. Min Act: -0.0001

Data Index: 1377346 (Python Code)

Max Activating Token Index: 715

Text #13

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4499. Min Act: -0.0001

Data Index: 1517432 (Python Code)

Max Activating Token Index: 934

Text #14

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4246. Min Act: -0.0001

Data Index: 1429584 (Python Code)

Max Activating Token Index: 132

Text #15

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4230. Min Act: -0.0001

Data Index: 1521793 (Python Code)

Max Activating Token Index: 890

Text #16

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4225. Min Act: -0.0001

Data Index: 1373487 (Python Code)

Max Activating Token Index: 47

Text #17

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4055. Min Act: -0.0001

Data Index: 1508019 (Python Code)

Max Activating Token Index: 648

Text #18

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.3867. Min Act: -0.0001

Data Index: 1531824 (Python Code)

Max Activating Token Index: 585

Text #19

Max Range: 0.5950. Min Range: -0.5950

Max Act: 0.4271. Min Act: -0.0001

Data Index: 1523267 (Python Code)

Max Activating Token Index: 718