Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 336 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1798. Min Range: -1.1798

Max Act: 1.1798. Min Act: -0.0001

Data Index: 1639775 (Python Code)

Max Activating Token Index: 8

Text #1

Max Range: 1.1798. Min Range: -1.1798

Max Act: 1.0928. Min Act: -0.0001

Data Index: 1507702 (Python Code)

Max Activating Token Index: 9

Text #2

Max Range: 1.1798. Min Range: -1.1798

Max Act: 1.1139. Min Act: -0.0001

Data Index: 1481471 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.9380. Min Act: -0.0001

Data Index: 1533180 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.9912. Min Act: -0.0001

Data Index: 1581130 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.9166. Min Act: -0.0001

Data Index: 1612561 (Python Code)

Max Activating Token Index: 10

Text #6

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.9413. Min Act: -0.0001

Data Index: 1447521 (Python Code)

Max Activating Token Index: 22

Text #7

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.9126. Min Act: -0.0001

Data Index: 1496824 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.9689. Min Act: -0.0001

Data Index: 1417031 (Python Code)

Max Activating Token Index: 17

Text #9

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.9504. Min Act: -0.0001

Data Index: 1605207 (Python Code)

Max Activating Token Index: 11

Text #10

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.8263. Min Act: -0.0001

Data Index: 1442465 (Python Code)

Max Activating Token Index: 623

Text #11

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.8866. Min Act: -0.0001

Data Index: 1463272 (Python Code)

Max Activating Token Index: 7

Text #12

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.8866. Min Act: -0.0001

Data Index: 1496637 (Python Code)

Max Activating Token Index: 7

Text #13

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.9142. Min Act: -0.0001

Data Index: 1536576 (Python Code)

Max Activating Token Index: 26

Text #14

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.8817. Min Act: -0.0001

Data Index: 1369487 (Python Code)

Max Activating Token Index: 6

Text #15

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.9648. Min Act: -0.0001

Data Index: 1441410 (Python Code)

Max Activating Token Index: 8

Text #16

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.8555. Min Act: -0.0001

Data Index: 1513490 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.7640. Min Act: -0.0001

Data Index: 1443428 (Python Code)

Max Activating Token Index: 315

Text #18

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.8380. Min Act: -0.0001

Data Index: 1545257 (Python Code)

Max Activating Token Index: 11

Text #19

Max Range: 1.1798. Min Range: -1.1798

Max Act: 0.8033. Min Act: -0.0001

Data Index: 1489812 (Python Code)

Max Activating Token Index: 142