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

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

Neuron 3478 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.1039. Min Act: -0.0000

Data Index: 112345 (C4 (Web Text))

Max Activating Token Index: 309

Text #1

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0864. Min Act: -0.0000

Data Index: 1152790 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0881. Min Act: -0.0000

Data Index: 1128807 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0900. Min Act: -0.0000

Data Index: 1199056 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0778. Min Act: -0.0000

Data Index: 1195258 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0824. Min Act: -0.0000

Data Index: 1016555 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0862. Min Act: -0.0000

Data Index: 201615 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0826. Min Act: -0.0000

Data Index: 807724 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0847. Min Act: -0.0000

Data Index: 222441 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0818. Min Act: -0.0000

Data Index: 1238518 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0772. Min Act: -0.0000

Data Index: 1348884 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0786. Min Act: -0.0000

Data Index: 80280 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0794. Min Act: -0.0000

Data Index: 1040432 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0762. Min Act: -0.0000

Data Index: 1006337 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0679. Min Act: -0.0000

Data Index: 1034829 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0792. Min Act: -0.0000

Data Index: 739206 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0698. Min Act: -0.0000

Data Index: 1095659 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0732. Min Act: -0.0000

Data Index: 486750 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0739. Min Act: -0.0000

Data Index: 486090 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.1039. Min Range: -0.1039

Max Act: 0.0760. Min Act: -0.0000

Data Index: 986980 (C4 (Web Text))

Max Activating Token Index: 396