Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2504 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1914. Min Act: -0.0001

Data Index: 1303003 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1981. Min Act: -0.0001

Data Index: 799742 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1809. Min Act: -0.0001

Data Index: 467933 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1786. Min Act: -0.0001

Data Index: 1061346 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1931. Min Act: -0.0001

Data Index: 401623 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1769. Min Act: -0.0001

Data Index: 802182 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1570. Min Act: -0.0001

Data Index: 767707 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1761. Min Act: -0.0001

Data Index: 1255917 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1657. Min Act: -0.0001

Data Index: 1091662 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1710. Min Act: -0.0001

Data Index: 112657 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1657. Min Act: -0.0001

Data Index: 1254188 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1837. Min Act: -0.0001

Data Index: 161783 (C4 (Web Text))

Max Activating Token Index: 502

Text #12

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1706. Min Act: -0.0001

Data Index: 1190623 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1692. Min Act: -0.0001

Data Index: 1022349 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1779. Min Act: -0.0001

Data Index: 325200 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1687. Min Act: -0.0001

Data Index: 743411 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1672. Min Act: -0.0001

Data Index: 1104783 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1615. Min Act: -0.0001

Data Index: 893211 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1540. Min Act: -0.0001

Data Index: 572648 (C4 (Web Text))

Max Activating Token Index: 190

Text #19

Max Range: 0.1981. Min Range: -0.1981

Max Act: 0.1601. Min Act: -0.0001

Data Index: 321024 (C4 (Web Text))

Max Activating Token Index: 747