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

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

Neuron 4807 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1899. Min Act: -0.0000

Data Index: 215741 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1872. Min Act: -0.0000

Data Index: 162493 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1831. Min Act: -0.0000

Data Index: 460063 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1704. Min Act: -0.0000

Data Index: 634431 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1801. Min Act: -0.0000

Data Index: 48200 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1744. Min Act: -0.0000

Data Index: 1298539 (C4 (Web Text))

Max Activating Token Index: 830

Text #6

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1630. Min Act: -0.0000

Data Index: 36683 (C4 (Web Text))

Max Activating Token Index: 690

Text #7

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1705. Min Act: -0.0000

Data Index: 841011 (C4 (Web Text))

Max Activating Token Index: 76

Text #8

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1687. Min Act: -0.0000

Data Index: 406389 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1664. Min Act: -0.0000

Data Index: 225546 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1670. Min Act: -0.0000

Data Index: 88235 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1705. Min Act: 0.0000

Data Index: 592866 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1630. Min Act: 0.0000

Data Index: 1177030 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1596. Min Act: -0.0000

Data Index: 63170 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1588. Min Act: -0.0000

Data Index: 746165 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1581. Min Act: -0.0000

Data Index: 899590 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1544. Min Act: -0.0000

Data Index: 960951 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1486. Min Act: 0.0000

Data Index: 882080 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1346. Min Act: -0.0000

Data Index: 1032666 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1418. Min Act: 0.0000

Data Index: 575684 (C4 (Web Text))

Max Activating Token Index: 806