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

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

Neuron 1118 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0874. Min Act: -0.0002

Data Index: 939155 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0689. Min Act: -0.0001

Data Index: 76170 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1197759 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0646. Min Act: -0.0001

Data Index: 752361 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0614. Min Act: -0.0001

Data Index: 1211272 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0665. Min Act: -0.0001

Data Index: 222697 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0639. Min Act: -0.0002

Data Index: 169613 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0683. Min Act: -0.0002

Data Index: 856972 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0623. Min Act: -0.0002

Data Index: 66863 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0628. Min Act: -0.0002

Data Index: 1223397 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0651. Min Act: -0.0002

Data Index: 1229294 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0650. Min Act: -0.0002

Data Index: 643427 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0643. Min Act: -0.0001

Data Index: 711566 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0646. Min Act: -0.0001

Data Index: 295673 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0620. Min Act: -0.0002

Data Index: 68236 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0586. Min Act: -0.0002

Data Index: 137607 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0600. Min Act: -0.0002

Data Index: 1354126 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1162432 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0620. Min Act: -0.0002

Data Index: 648471 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 0.0874. Min Range: -0.0874

Max Act: 0.0629. Min Act: -0.0002

Data Index: 189386 (C4 (Web Text))

Max Activating Token Index: 943