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

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

Neuron 6114 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.7008. Min Act: -0.0000

Data Index: 1485147 (Python Code)

Max Activating Token Index: 421

Text #1

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1424028 (Python Code)

Max Activating Token Index: 751

Text #2

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1570916 (Python Code)

Max Activating Token Index: 416

Text #3

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.5523. Min Act: -0.0000

Data Index: 1377576 (Python Code)

Max Activating Token Index: 560

Text #4

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.5647. Min Act: -0.0000

Data Index: 1462028 (Python Code)

Max Activating Token Index: 837

Text #5

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1505761 (Python Code)

Max Activating Token Index: 230

Text #6

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.5337. Min Act: -0.0000

Data Index: 255734 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.5056. Min Act: -0.0000

Data Index: 1532646 (Python Code)

Max Activating Token Index: 243

Text #8

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1195527 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1425855 (Python Code)

Max Activating Token Index: 143

Text #10

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.5172. Min Act: -0.0000

Data Index: 1587696 (Python Code)

Max Activating Token Index: 107

Text #11

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.4862. Min Act: -0.0000

Data Index: 1638583 (Python Code)

Max Activating Token Index: 1006

Text #12

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.4749. Min Act: -0.0000

Data Index: 1480749 (Python Code)

Max Activating Token Index: 964

Text #13

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.4730. Min Act: -0.0000

Data Index: 1452821 (Python Code)

Max Activating Token Index: 624

Text #14

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.5006. Min Act: -0.0000

Data Index: 325561 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1486590 (Python Code)

Max Activating Token Index: 157

Text #16

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.4766. Min Act: -0.0000

Data Index: 1519805 (Python Code)

Max Activating Token Index: 572

Text #17

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.4727. Min Act: -0.0000

Data Index: 1406573 (Python Code)

Max Activating Token Index: 661

Text #18

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.4738. Min Act: -0.0000

Data Index: 874563 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 0.7008. Min Range: -0.7008

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1525236 (Python Code)

Max Activating Token Index: 888