Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 667 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1959. Min Act: -0.0003

Data Index: 1113734 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1975. Min Act: -0.0003

Data Index: 1344625 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1836. Min Act: -0.0004

Data Index: 525683 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1620. Min Act: -0.0002

Data Index: 927032 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1556. Min Act: -0.0003

Data Index: 649628 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1680. Min Act: -0.0003

Data Index: 529092 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1724. Min Act: -0.0003

Data Index: 368844 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1630. Min Act: -0.0004

Data Index: 96791 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1658. Min Act: -0.0003

Data Index: 1352990 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1666. Min Act: -0.0003

Data Index: 1243157 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1662. Min Act: -0.0003

Data Index: 648219 (C4 (Web Text))

Max Activating Token Index: 621

Text #11

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1636. Min Act: -0.0003

Data Index: 1293259 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1665. Min Act: -0.0003

Data Index: 677625 (C4 (Web Text))

Max Activating Token Index: 647

Text #13

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1652. Min Act: -0.0003

Data Index: 500343 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1637. Min Act: -0.0003

Data Index: 1022989 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1674. Min Act: -0.0003

Data Index: 805172 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1678. Min Act: -0.0003

Data Index: 85859 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1768. Min Act: -0.0003

Data Index: 432674 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1683. Min Act: -0.0003

Data Index: 723823 (C4 (Web Text))

Max Activating Token Index: 625

Text #19

Max Range: 0.1975. Min Range: -0.1975

Max Act: 0.1606. Min Act: -0.0003

Data Index: 437540 (C4 (Web Text))

Max Activating Token Index: 703