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

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

Neuron 2294 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.9689. Min Act: -0.0000

Data Index: 1572336 (Python Code)

Max Activating Token Index: 1005

Text #1

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.8809. Min Act: -0.0000

Data Index: 1500307 (Python Code)

Max Activating Token Index: 73

Text #2

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.8619. Min Act: -0.0000

Data Index: 1544640 (Python Code)

Max Activating Token Index: 894

Text #3

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.8633. Min Act: -0.0000

Data Index: 1597740 (Python Code)

Max Activating Token Index: 714

Text #4

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.8306. Min Act: -0.0000

Data Index: 1589698 (Python Code)

Max Activating Token Index: 930

Text #5

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.8149. Min Act: -0.0000

Data Index: 1377926 (Python Code)

Max Activating Token Index: 815

Text #6

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.7429. Min Act: -0.0000

Data Index: 1571068 (Python Code)

Max Activating Token Index: 829

Text #7

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.7176. Min Act: -0.0000

Data Index: 1606601 (Python Code)

Max Activating Token Index: 608

Text #8

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.6940. Min Act: -0.0000

Data Index: 1369422 (Python Code)

Max Activating Token Index: 225

Text #9

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.8123. Min Act: -0.0000

Data Index: 1387599 (Python Code)

Max Activating Token Index: 984

Text #10

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.6385. Min Act: -0.0000

Data Index: 1565987 (Python Code)

Max Activating Token Index: 1008

Text #11

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.6437. Min Act: -0.0000

Data Index: 1419105 (Python Code)

Max Activating Token Index: 983

Text #12

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.6262. Min Act: -0.0000

Data Index: 1429577 (Python Code)

Max Activating Token Index: 955

Text #13

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.5037. Min Act: -0.0000

Data Index: 1423946 (Python Code)

Max Activating Token Index: 999

Text #14

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.6253. Min Act: -0.0000

Data Index: 1467720 (Python Code)

Max Activating Token Index: 1019

Text #15

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.6134. Min Act: -0.0000

Data Index: 1656620 (Python Code)

Max Activating Token Index: 505

Text #16

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.6232. Min Act: -0.0000

Data Index: 1520192 (Python Code)

Max Activating Token Index: 952

Text #17

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.6120. Min Act: -0.0000

Data Index: 1580873 (Python Code)

Max Activating Token Index: 756

Text #18

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.5358. Min Act: -0.0000

Data Index: 1494957 (Python Code)

Max Activating Token Index: 739

Text #19

Max Range: 2.9689. Min Range: -2.9689

Max Act: 2.6329. Min Act: -0.0000

Data Index: 1563515 (Python Code)

Max Activating Token Index: 986