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

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

Neuron 4388 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.1015. Min Act: -0.0001

Data Index: 1099397 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0877. Min Act: -0.0001

Data Index: 188185 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0879. Min Act: -0.0001

Data Index: 998943 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0780. Min Act: -0.0001

Data Index: 46090 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0769. Min Act: -0.0001

Data Index: 512829 (C4 (Web Text))

Max Activating Token Index: 476

Text #5

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0782. Min Act: -0.0001

Data Index: 1148766 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1239211 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1151309 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0790. Min Act: -0.0001

Data Index: 877445 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0772. Min Act: -0.0001

Data Index: 569071 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0758. Min Act: -0.0001

Data Index: 201866 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1126780 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0787. Min Act: -0.0001

Data Index: 1331903 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0794. Min Act: -0.0001

Data Index: 1082492 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0745. Min Act: -0.0001

Data Index: 301868 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0700. Min Act: -0.0001

Data Index: 293822 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0713. Min Act: -0.0001

Data Index: 986961 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0714. Min Act: -0.0001

Data Index: 52291 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0774. Min Act: -0.0001

Data Index: 953280 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.1015. Min Range: -0.1015

Max Act: 0.0750. Min Act: -0.0001

Data Index: 163854 (C4 (Web Text))

Max Activating Token Index: 234