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

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

Neuron 5623 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: 0.0766. Min Range: -0.0766

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1208950 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0646. Min Act: -0.0002

Data Index: 837729 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0623. Min Act: -0.0002

Data Index: 121615 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1089394 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1201300 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0588. Min Act: -0.0002

Data Index: 685188 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0594. Min Act: -0.0002

Data Index: 668785 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0536. Min Act: -0.0002

Data Index: 480783 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0535. Min Act: -0.0002

Data Index: 480086 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1032465 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0497. Min Act: -0.0002

Data Index: 125553 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0528. Min Act: -0.0002

Data Index: 317124 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0484. Min Act: -0.0002

Data Index: 1317295 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0470. Min Act: -0.0002

Data Index: 825685 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0460. Min Act: -0.0002

Data Index: 946583 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0442. Min Act: -0.0002

Data Index: 965038 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1182306 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0444. Min Act: -0.0002

Data Index: 855340 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0404. Min Act: -0.0002

Data Index: 647213 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1147084 (C4 (Web Text))

Max Activating Token Index: 142