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

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

Neuron 3384 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 10.0894. Min Range: -10.0894

Max Act: 10.0894. Min Act: -0.0001

Data Index: 1563494 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 10.0894. Min Range: -10.0894

Max Act: 9.8979. Min Act: -0.0001

Data Index: 1365107 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 10.0894. Min Range: -10.0894

Max Act: 9.4734. Min Act: -0.0001

Data Index: 1656716 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 10.0894. Min Range: -10.0894

Max Act: 9.4649. Min Act: -0.0001

Data Index: 1579379 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 10.0894. Min Range: -10.0894

Max Act: 9.4808. Min Act: -0.0001

Data Index: 1648617 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 10.0894. Min Range: -10.0894

Max Act: 9.2457. Min Act: -0.0001

Data Index: 1481919 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 10.0894. Min Range: -10.0894

Max Act: 9.1352. Min Act: -0.0001

Data Index: 1566868 (Python Code)

Max Activating Token Index: 4

Text #7

Max Range: 10.0894. Min Range: -10.0894

Max Act: 9.1352. Min Act: -0.0001

Data Index: 1593221 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 10.0894. Min Range: -10.0894

Max Act: 9.2473. Min Act: -0.0001

Data Index: 1509281 (Python Code)

Max Activating Token Index: 6

Text #9

Max Range: 10.0894. Min Range: -10.0894

Max Act: 9.1234. Min Act: -0.0002

Data Index: 1504544 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 10.0894. Min Range: -10.0894

Max Act: 9.1234. Min Act: -0.0001

Data Index: 1435520 (Python Code)

Max Activating Token Index: 4

Text #11

Max Range: 10.0894. Min Range: -10.0894

Max Act: 8.9974. Min Act: -0.0001

Data Index: 1404171 (Python Code)

Max Activating Token Index: 5

Text #12

Max Range: 10.0894. Min Range: -10.0894

Max Act: 8.6481. Min Act: -0.0001

Data Index: 1402153 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 10.0894. Min Range: -10.0894

Max Act: 8.4997. Min Act: -0.0001

Data Index: 1362829 (Python Code)

Max Activating Token Index: 3

Text #14

Max Range: 10.0894. Min Range: -10.0894

Max Act: 8.2531. Min Act: -0.0001

Data Index: 1430807 (Python Code)

Max Activating Token Index: 9

Text #15

Max Range: 10.0894. Min Range: -10.0894

Max Act: 8.3845. Min Act: -0.0001

Data Index: 1507289 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 10.0894. Min Range: -10.0894

Max Act: 8.5101. Min Act: -0.0001

Data Index: 1434550 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 10.0894. Min Range: -10.0894

Max Act: 8.5101. Min Act: -0.0001

Data Index: 1554783 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 10.0894. Min Range: -10.0894

Max Act: 8.3719. Min Act: -0.0001

Data Index: 1475014 (Python Code)

Max Activating Token Index: 8

Text #19

Max Range: 10.0894. Min Range: -10.0894

Max Act: 8.2444. Min Act: -0.0001

Data Index: 1428394 (Python Code)

Max Activating Token Index: 3