Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 395 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1600. Min Range: -1.1600

Max Act: 1.1600. Min Act: -0.0001

Data Index: 1497376 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9953. Min Act: -0.0001

Data Index: 1484551 (Python Code)

Max Activating Token Index: 28

Text #2

Max Range: 1.1600. Min Range: -1.1600

Max Act: 1.0120. Min Act: -0.0001

Data Index: 1409292 (Python Code)

Max Activating Token Index: 20

Text #3

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9907. Min Act: -0.0001

Data Index: 1585538 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9798. Min Act: -0.0001

Data Index: 1363152 (Python Code)

Max Activating Token Index: 10

Text #5

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9559. Min Act: -0.0001

Data Index: 1469981 (Python Code)

Max Activating Token Index: 922

Text #6

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9800. Min Act: -0.0001

Data Index: 1607334 (Python Code)

Max Activating Token Index: 18

Text #7

Max Range: 1.1600. Min Range: -1.1600

Max Act: 1.0109. Min Act: -0.0001

Data Index: 1559674 (Python Code)

Max Activating Token Index: 30

Text #8

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9513. Min Act: -0.0001

Data Index: 1589450 (Python Code)

Max Activating Token Index: 30

Text #9

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9481. Min Act: -0.0001

Data Index: 1504568 (Python Code)

Max Activating Token Index: 88

Text #10

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9151. Min Act: -0.0001

Data Index: 1443459 (Python Code)

Max Activating Token Index: 16

Text #11

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9139. Min Act: -0.0001

Data Index: 1607837 (Python Code)

Max Activating Token Index: 689

Text #12

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9278. Min Act: -0.0001

Data Index: 1480817 (Python Code)

Max Activating Token Index: 567

Text #13

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9251. Min Act: -0.0001

Data Index: 1438012 (Python Code)

Max Activating Token Index: 854

Text #14

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9554. Min Act: -0.0001

Data Index: 1567146 (Python Code)

Max Activating Token Index: 326

Text #15

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9238. Min Act: -0.0001

Data Index: 1376805 (Python Code)

Max Activating Token Index: 253

Text #16

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8481. Min Act: -0.0001

Data Index: 1389644 (Python Code)

Max Activating Token Index: 1014

Text #17

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.9472. Min Act: -0.0001

Data Index: 1450974 (Python Code)

Max Activating Token Index: 893

Text #18

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8903. Min Act: -0.0001

Data Index: 1359912 (Python Code)

Max Activating Token Index: 708

Text #19

Max Range: 1.1600. Min Range: -1.1600

Max Act: 0.8859. Min Act: -0.0001

Data Index: 1424039 (Python Code)

Max Activating Token Index: 11