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

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

Neuron 537 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.8758. Min Act: -0.0000

Data Index: 1456031 (Python Code)

Max Activating Token Index: 42

Text #1

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.6518. Min Act: -0.0000

Data Index: 1525627 (Python Code)

Max Activating Token Index: 391

Text #2

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.6740. Min Act: -0.0000

Data Index: 1387843 (Python Code)

Max Activating Token Index: 101

Text #3

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1433667 (Python Code)

Max Activating Token Index: 275

Text #4

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.6737. Min Act: -0.0000

Data Index: 1398077 (Python Code)

Max Activating Token Index: 62

Text #5

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.6955. Min Act: -0.0001

Data Index: 1526891 (Python Code)

Max Activating Token Index: 43

Text #6

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.6475. Min Act: -0.0000

Data Index: 1515328 (Python Code)

Max Activating Token Index: 283

Text #7

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1581697 (Python Code)

Max Activating Token Index: 217

Text #8

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.6782. Min Act: -0.0000

Data Index: 1412850 (Python Code)

Max Activating Token Index: 172

Text #9

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.6563. Min Act: -0.0000

Data Index: 1429797 (Python Code)

Max Activating Token Index: 45

Text #10

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.6315. Min Act: -0.0000

Data Index: 1403851 (Python Code)

Max Activating Token Index: 26

Text #11

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.6332. Min Act: -0.0000

Data Index: 1468591 (Python Code)

Max Activating Token Index: 69

Text #12

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1462446 (Python Code)

Max Activating Token Index: 80

Text #13

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1577303 (Python Code)

Max Activating Token Index: 56

Text #14

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.6578. Min Act: -0.0001

Data Index: 1419918 (Python Code)

Max Activating Token Index: 88

Text #15

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.6306. Min Act: -0.0000

Data Index: 1589525 (Python Code)

Max Activating Token Index: 144

Text #16

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.6174. Min Act: -0.0000

Data Index: 1400150 (Python Code)

Max Activating Token Index: 87

Text #17

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.6109. Min Act: -0.0000

Data Index: 1617645 (Python Code)

Max Activating Token Index: 50

Text #18

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.5912. Min Act: -0.0000

Data Index: 1628132 (Python Code)

Max Activating Token Index: 32

Text #19

Max Range: 0.8758. Min Range: -0.8758

Max Act: 0.5667. Min Act: -0.0000

Data Index: 1598334 (Python Code)

Max Activating Token Index: 163