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

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

Neuron 1751 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3568. Min Act: -0.0000

Data Index: 1594022 (Python Code)

Max Activating Token Index: 494

Text #1

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3021. Min Act: 0.0001

Data Index: 1361149 (Python Code)

Max Activating Token Index: 161

Text #2

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2824. Min Act: 0.0001

Data Index: 900948 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2896. Min Act: -0.0000

Data Index: 199954 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2858. Min Act: 0.0000

Data Index: 1591465 (Python Code)

Max Activating Token Index: 848

Text #5

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2730. Min Act: -0.0000

Data Index: 1347452 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3028. Min Act: -0.0000

Data Index: 423575 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2920. Min Act: -0.0000

Data Index: 1567733 (Python Code)

Max Activating Token Index: 810

Text #8

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2596. Min Act: -0.0000

Data Index: 1046004 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2560. Min Act: -0.0000

Data Index: 1484747 (Python Code)

Max Activating Token Index: 266

Text #10

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2511. Min Act: -0.0000

Data Index: 387648 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2660. Min Act: -0.0000

Data Index: 1325565 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2527. Min Act: -0.0000

Data Index: 812779 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2374. Min Act: -0.0000

Data Index: 604872 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2529. Min Act: -0.0000

Data Index: 351462 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2445. Min Act: -0.0000

Data Index: 1204975 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2610. Min Act: -0.0000

Data Index: 360836 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2489. Min Act: -0.0000

Data Index: 792481 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2666. Min Act: -0.0000

Data Index: 628772 (C4 (Web Text))

Max Activating Token Index: 918

Text #19

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2413. Min Act: -0.0000

Data Index: 1577600 (Python Code)

Max Activating Token Index: 573