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

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

Neuron 3299 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.6204. Min Act: -0.0000

Data Index: 1453284 (Python Code)

Max Activating Token Index: 646

Text #1

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1498346 (Python Code)

Max Activating Token Index: 501

Text #2

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1440940 (Python Code)

Max Activating Token Index: 177

Text #3

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.5008. Min Act: -0.0000

Data Index: 1555305 (Python Code)

Max Activating Token Index: 393

Text #4

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.5606. Min Act: -0.0000

Data Index: 1632104 (Python Code)

Max Activating Token Index: 209

Text #5

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.5741. Min Act: -0.0000

Data Index: 1630355 (Python Code)

Max Activating Token Index: 87

Text #6

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.3492. Min Act: -0.0000

Data Index: 1553853 (Python Code)

Max Activating Token Index: 919

Text #7

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.5884. Min Act: -0.0000

Data Index: 1522105 (Python Code)

Max Activating Token Index: 461

Text #8

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.5493. Min Act: -0.0000

Data Index: 1531484 (Python Code)

Max Activating Token Index: 86

Text #9

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4631. Min Act: -0.0000

Data Index: 1517720 (Python Code)

Max Activating Token Index: 360

Text #10

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1401510 (Python Code)

Max Activating Token Index: 542

Text #11

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1621190 (Python Code)

Max Activating Token Index: 694

Text #12

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.5791. Min Act: -0.0000

Data Index: 1407282 (Python Code)

Max Activating Token Index: 605

Text #13

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.5302. Min Act: -0.0000

Data Index: 1375137 (Python Code)

Max Activating Token Index: 443

Text #14

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1360566 (Python Code)

Max Activating Token Index: 518

Text #15

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1528058 (Python Code)

Max Activating Token Index: 717

Text #16

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1525420 (Python Code)

Max Activating Token Index: 393

Text #17

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1424935 (Python Code)

Max Activating Token Index: 985

Text #18

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.3946. Min Act: -0.0000

Data Index: 1584373 (Python Code)

Max Activating Token Index: 880

Text #19

Max Range: 0.6611. Min Range: -0.6611

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1646490 (Python Code)

Max Activating Token Index: 701