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

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

Neuron 1853 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.2027. Min Act: -0.0000

Data Index: 382589 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1960. Min Act: -0.0000

Data Index: 897787 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1057803 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1779. Min Act: -0.0000

Data Index: 988833 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1685. Min Act: -0.0000

Data Index: 126281 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1829. Min Act: -0.0000

Data Index: 871144 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1697. Min Act: -0.0000

Data Index: 392794 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1763. Min Act: -0.0000

Data Index: 445749 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1721. Min Act: -0.0000

Data Index: 532493 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1540. Min Act: -0.0000

Data Index: 1254692 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1575. Min Act: -0.0000

Data Index: 308658 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1624. Min Act: -0.0000

Data Index: 951782 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1664. Min Act: -0.0000

Data Index: 715397 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1536. Min Act: -0.0000

Data Index: 148751 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1653. Min Act: -0.0000

Data Index: 374173 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1584. Min Act: -0.0000

Data Index: 383721 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1515. Min Act: -0.0000

Data Index: 1321343 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1510. Min Act: -0.0000

Data Index: 259154 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1390. Min Act: -0.0000

Data Index: 465406 (C4 (Web Text))

Max Activating Token Index: 691

Text #19

Max Range: 0.2027. Min Range: -0.2027

Max Act: 0.1544. Min Act: -0.0000

Data Index: 86314 (C4 (Web Text))

Max Activating Token Index: 774