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

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

Neuron 2885 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.2035. Min Act: -0.0000

Data Index: 1311135 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1712. Min Act: -0.0000

Data Index: 19135 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1705. Min Act: -0.0000

Data Index: 1101336 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1645. Min Act: -0.0000

Data Index: 986033 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1689. Min Act: -0.0000

Data Index: 962992 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1675. Min Act: -0.0000

Data Index: 627271 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1664. Min Act: -0.0000

Data Index: 1285039 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1630. Min Act: -0.0000

Data Index: 755779 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1758. Min Act: -0.0000

Data Index: 497723 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1701. Min Act: -0.0000

Data Index: 465815 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1523. Min Act: -0.0000

Data Index: 619264 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1611. Min Act: -0.0000

Data Index: 736705 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1601. Min Act: -0.0000

Data Index: 208870 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1590. Min Act: -0.0000

Data Index: 975587 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1645. Min Act: -0.0000

Data Index: 289078 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1535. Min Act: -0.0000

Data Index: 886237 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1485. Min Act: -0.0000

Data Index: 1204283 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1496. Min Act: -0.0000

Data Index: 46567 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1456. Min Act: -0.0000

Data Index: 470193 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.2035. Min Range: -0.2035

Max Act: 0.1497. Min Act: -0.0000

Data Index: 680170 (C4 (Web Text))

Max Activating Token Index: 480