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

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

Neuron 2621 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5971. Min Range: -3.5971

Max Act: 3.5971. Min Act: -0.0000

Data Index: 1458915 (Python Code)

Max Activating Token Index: 783

Text #1

Max Range: 3.5971. Min Range: -3.5971

Max Act: 2.6325. Min Act: 0.0001

Data Index: 1570708 (Python Code)

Max Activating Token Index: 454

Text #2

Max Range: 3.5971. Min Range: -3.5971

Max Act: 2.3862. Min Act: -0.0000

Data Index: 1432379 (Python Code)

Max Activating Token Index: 24

Text #3

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.9488. Min Act: -0.0000

Data Index: 1609919 (Python Code)

Max Activating Token Index: 280

Text #4

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.9022. Min Act: 0.0000

Data Index: 1610268 (Python Code)

Max Activating Token Index: 777

Text #5

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.8880. Min Act: -0.0000

Data Index: 1550671 (Python Code)

Max Activating Token Index: 496

Text #6

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.5799. Min Act: 0.0000

Data Index: 1536589 (Python Code)

Max Activating Token Index: 467

Text #7

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.5662. Min Act: -0.0000

Data Index: 1556294 (Python Code)

Max Activating Token Index: 535

Text #8

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.5160. Min Act: -0.0000

Data Index: 1594682 (Python Code)

Max Activating Token Index: 875

Text #9

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.5175. Min Act: -0.0000

Data Index: 1515853 (Python Code)

Max Activating Token Index: 681

Text #10

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.4128. Min Act: -0.0000

Data Index: 1541245 (Python Code)

Max Activating Token Index: 1001

Text #11

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.4361. Min Act: -0.0000

Data Index: 1618173 (Python Code)

Max Activating Token Index: 138

Text #12

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.3582. Min Act: -0.0000

Data Index: 1654317 (Python Code)

Max Activating Token Index: 911

Text #13

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.3448. Min Act: -0.0000

Data Index: 1445603 (Python Code)

Max Activating Token Index: 586

Text #14

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.3582. Min Act: -0.0000

Data Index: 1570591 (Python Code)

Max Activating Token Index: 540

Text #15

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.2452. Min Act: -0.0000

Data Index: 1429581 (Python Code)

Max Activating Token Index: 241

Text #16

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.1622. Min Act: -0.0000

Data Index: 1656239 (Python Code)

Max Activating Token Index: 423

Text #17

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.2369. Min Act: -0.0000

Data Index: 1515817 (Python Code)

Max Activating Token Index: 494

Text #18

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.1832. Min Act: -0.0000

Data Index: 1440650 (Python Code)

Max Activating Token Index: 59

Text #19

Max Range: 3.5971. Min Range: -3.5971

Max Act: 1.1379. Min Act: -0.0000

Data Index: 1565899 (Python Code)

Max Activating Token Index: 540