Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1556 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1823. Min Act: -0.0000

Data Index: 1243654 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.2115. Min Act: -0.0000

Data Index: 891384 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.2055. Min Act: -0.0001

Data Index: 473483 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.2159. Min Act: -0.0001

Data Index: 439284 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1925. Min Act: -0.0001

Data Index: 181564 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1981. Min Act: -0.0001

Data Index: 970034 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1854. Min Act: -0.0001

Data Index: 725422 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1811. Min Act: -0.0000

Data Index: 1122210 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1816. Min Act: -0.0000

Data Index: 332580 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1759. Min Act: -0.0000

Data Index: 125407 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1777. Min Act: -0.0000

Data Index: 813526 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1632. Min Act: -0.0001

Data Index: 1087612 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1659. Min Act: -0.0000

Data Index: 990691 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1698. Min Act: -0.0001

Data Index: 744497 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1832. Min Act: -0.0001

Data Index: 385096 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1628. Min Act: -0.0001

Data Index: 142370 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1676. Min Act: -0.0000

Data Index: 1130962 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1506. Min Act: -0.0001

Data Index: 746121 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1669. Min Act: -0.0001

Data Index: 410919 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.2159. Min Range: -0.2159

Max Act: 0.1717. Min Act: -0.0000

Data Index: 501014 (C4 (Web Text))

Max Activating Token Index: 420