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

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

Neuron 5613 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0133. Min Range: -1.0133

Max Act: 1.0133. Min Act: -0.0002

Data Index: 1163995 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.9384. Min Act: -0.0002

Data Index: 1165859 (C4 (Web Text))

Max Activating Token Index: 559

Text #2

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.9604. Min Act: -0.0002

Data Index: 823989 (C4 (Web Text))

Max Activating Token Index: 446

Text #3

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8811. Min Act: -0.0002

Data Index: 811260 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8128. Min Act: -0.0002

Data Index: 943938 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8572. Min Act: -0.0002

Data Index: 518163 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8476. Min Act: -0.0002

Data Index: 1294294 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8073. Min Act: -0.0002

Data Index: 430895 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8028. Min Act: -0.0002

Data Index: 803398 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8086. Min Act: -0.0002

Data Index: 1034878 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8264. Min Act: -0.0002

Data Index: 1286612 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.8084. Min Act: -0.0002

Data Index: 293281 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7762. Min Act: -0.0002

Data Index: 545248 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7944. Min Act: -0.0002

Data Index: 847893 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7680. Min Act: -0.0002

Data Index: 1098062 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7682. Min Act: -0.0002

Data Index: 683621 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7850. Min Act: -0.0002

Data Index: 1137823 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7560. Min Act: -0.0002

Data Index: 667926 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7774. Min Act: -0.0002

Data Index: 482015 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 1.0133. Min Range: -1.0133

Max Act: 0.7702. Min Act: -0.0002

Data Index: 637134 (C4 (Web Text))

Max Activating Token Index: 92