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

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

Neuron 1547 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.3832. Min Act: -0.0000

Data Index: 415048 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.3449. Min Act: -0.0000

Data Index: 1343197 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.3704. Min Act: -0.0000

Data Index: 698224 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2834. Min Act: -0.0000

Data Index: 83861 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.3046. Min Act: -0.0000

Data Index: 490164 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2816. Min Act: -0.0000

Data Index: 1049203 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2834. Min Act: -0.0000

Data Index: 1337944 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2726. Min Act: -0.0000

Data Index: 1273442 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2622. Min Act: -0.0000

Data Index: 593186 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2625. Min Act: -0.0000

Data Index: 767356 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2464. Min Act: -0.0000

Data Index: 730515 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2538. Min Act: -0.0000

Data Index: 403026 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2626. Min Act: -0.0000

Data Index: 618029 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1617452 (Python Code)

Max Activating Token Index: 730

Text #14

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2518. Min Act: -0.0000

Data Index: 1259340 (C4 (Web Text))

Max Activating Token Index: 845

Text #15

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2439. Min Act: -0.0000

Data Index: 415085 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2582. Min Act: -0.0000

Data Index: 507581 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2345. Min Act: -0.0000

Data Index: 216139 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2471. Min Act: -0.0000

Data Index: 794613 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 0.3832. Min Range: -0.3832

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1307542 (C4 (Web Text))

Max Activating Token Index: 218