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

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

Neuron 5125 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3307. Min Range: -4.3307

Max Act: 4.3307. Min Act: -0.0000

Data Index: 320358 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 4.3307. Min Range: -4.3307

Max Act: 3.6489. Min Act: -0.0000

Data Index: 746405 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 4.3307. Min Range: -4.3307

Max Act: 3.7187. Min Act: -0.0000

Data Index: 1260656 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 4.3307. Min Range: -4.3307

Max Act: 3.6425. Min Act: -0.0000

Data Index: 621816 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 4.3307. Min Range: -4.3307

Max Act: 3.5719. Min Act: -0.0000

Data Index: 1311104 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 4.3307. Min Range: -4.3307

Max Act: 3.5427. Min Act: -0.0000

Data Index: 815509 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 4.3307. Min Range: -4.3307

Max Act: 3.4823. Min Act: -0.0000

Data Index: 27463 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 4.3307. Min Range: -4.3307

Max Act: 3.3561. Min Act: -0.0000

Data Index: 360058 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 4.3307. Min Range: -4.3307

Max Act: 3.1767. Min Act: -0.0000

Data Index: 1211587 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 4.3307. Min Range: -4.3307

Max Act: 2.9630. Min Act: -0.0000

Data Index: 695530 (C4 (Web Text))

Max Activating Token Index: 342

Text #10

Max Range: 4.3307. Min Range: -4.3307

Max Act: 3.2121. Min Act: -0.0000

Data Index: 497067 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 4.3307. Min Range: -4.3307

Max Act: 3.0904. Min Act: -0.0000

Data Index: 324508 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 4.3307. Min Range: -4.3307

Max Act: 2.9551. Min Act: -0.0000

Data Index: 267338 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 4.3307. Min Range: -4.3307

Max Act: 2.9602. Min Act: -0.0000

Data Index: 593230 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 4.3307. Min Range: -4.3307

Max Act: 2.8698. Min Act: -0.0000

Data Index: 891526 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 4.3307. Min Range: -4.3307

Max Act: 2.6808. Min Act: -0.0000

Data Index: 390200 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 4.3307. Min Range: -4.3307

Max Act: 2.6804. Min Act: -0.0000

Data Index: 1196227 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 4.3307. Min Range: -4.3307

Max Act: 2.5449. Min Act: -0.0000

Data Index: 378971 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 4.3307. Min Range: -4.3307

Max Act: 2.4715. Min Act: -0.0000

Data Index: 1267225 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 4.3307. Min Range: -4.3307

Max Act: 2.3011. Min Act: -0.0000

Data Index: 528505 (C4 (Web Text))

Max Activating Token Index: 601