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

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

Neuron 1556 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7420. Min Act: -0.0002

Data Index: 1509281 (Python Code)

Max Activating Token Index: 15

Text #1

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7930. Min Act: -0.0002

Data Index: 1645165 (Python Code)

Max Activating Token Index: 51

Text #2

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7435. Min Act: -0.0002

Data Index: 1589376 (Python Code)

Max Activating Token Index: 414

Text #3

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7041. Min Act: -0.0002

Data Index: 1575017 (Python Code)

Max Activating Token Index: 961

Text #4

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.6648. Min Act: -0.0002

Data Index: 1455686 (Python Code)

Max Activating Token Index: 247

Text #5

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7156. Min Act: -0.0002

Data Index: 1380268 (Python Code)

Max Activating Token Index: 169

Text #6

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7233. Min Act: -0.0002

Data Index: 1508249 (Python Code)

Max Activating Token Index: 18

Text #7

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7506. Min Act: -0.0002

Data Index: 1547965 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7686. Min Act: -0.0002

Data Index: 1619957 (Python Code)

Max Activating Token Index: 40

Text #9

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7640. Min Act: -0.0002

Data Index: 1433270 (Python Code)

Max Activating Token Index: 28

Text #10

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.6717. Min Act: -0.0002

Data Index: 1534424 (Python Code)

Max Activating Token Index: 54

Text #11

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.6349. Min Act: -0.0002

Data Index: 1598952 (Python Code)

Max Activating Token Index: 158

Text #12

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.6631. Min Act: -0.0002

Data Index: 1427582 (Python Code)

Max Activating Token Index: 124

Text #13

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7057. Min Act: -0.0002

Data Index: 1589408 (Python Code)

Max Activating Token Index: 252

Text #14

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7102. Min Act: -0.0002

Data Index: 1459812 (Python Code)

Max Activating Token Index: 382

Text #15

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.6876. Min Act: -0.0002

Data Index: 1443263 (Python Code)

Max Activating Token Index: 550

Text #16

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7179. Min Act: -0.0002

Data Index: 1433972 (Python Code)

Max Activating Token Index: 316

Text #17

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7389. Min Act: -0.0002

Data Index: 1457972 (Python Code)

Max Activating Token Index: 918

Text #18

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.6501. Min Act: -0.0002

Data Index: 1462030 (Python Code)

Max Activating Token Index: 830

Text #19

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.6528. Min Act: -0.0002

Data Index: 1524471 (Python Code)

Max Activating Token Index: 366