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

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

Neuron 3626 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2429. Min Range: -0.2429

Max Act: 0.2429. Min Act: -0.0000

Data Index: 314670 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 0.2429. Min Range: -0.2429

Max Act: 0.2183. Min Act: -0.0000

Data Index: 820774 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 0.2429. Min Range: -0.2429

Max Act: 0.2014. Min Act: -0.0000

Data Index: 684354 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 0.2429. Min Range: -0.2429

Max Act: 0.1982. Min Act: -0.0000

Data Index: 847168 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.2429. Min Range: -0.2429

Max Act: 0.1821. Min Act: -0.0000

Data Index: 837406 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.2429. Min Range: -0.2429

Max Act: 0.1824. Min Act: -0.0000

Data Index: 276983 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 0.2429. Min Range: -0.2429

Max Act: 0.1620. Min Act: -0.0000

Data Index: 504109 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.2429. Min Range: -0.2429

Max Act: 0.1745. Min Act: -0.0000

Data Index: 1636268 (Python Code)

Max Activating Token Index: 240

Text #8

Max Range: 0.2429. Min Range: -0.2429

Max Act: 0.1608. Min Act: -0.0000

Data Index: 1550882 (Python Code)

Max Activating Token Index: 290

Text #9

Max Range: 0.2429. Min Range: -0.2429

Max Act: 0.1686. Min Act: -0.0000

Data Index: 445160 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 0.2429. Min Range: -0.2429

Max Act: 0.1692. Min Act: -0.0000

Data Index: 852866 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 0.2429. Min Range: -0.2429

Max Act: 0.1596. Min Act: -0.0000

Data Index: 106524 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 0.2429. Min Range: -0.2429

Max Act: 0.1814. Min Act: -0.0000

Data Index: 917501 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.2429. Min Range: -0.2429

Max Act: 0.1575. Min Act: -0.0000

Data Index: 94267 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.2429. Min Range: -0.2429

Max Act: 0.1540. Min Act: -0.0000

Data Index: 1146087 (C4 (Web Text))

Max Activating Token Index: 259

Text #15

Max Range: 0.2429. Min Range: -0.2429

Max Act: 0.1645. Min Act: -0.0000

Data Index: 552233 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 0.2429. Min Range: -0.2429

Max Act: 0.1560. Min Act: 0.0001

Data Index: 726746 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.2429. Min Range: -0.2429

Max Act: 0.1561. Min Act: -0.0000

Data Index: 750343 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 0.2429. Min Range: -0.2429

Max Act: 0.1549. Min Act: -0.0000

Data Index: 1642732 (Python Code)

Max Activating Token Index: 350

Text #19

Max Range: 0.2429. Min Range: -0.2429

Max Act: 0.1548. Min Act: -0.0000

Data Index: 374389 (C4 (Web Text))

Max Activating Token Index: 927