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

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

Neuron 3590 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.7038. Min Act: -0.0000

Data Index: 1402780 (Python Code)

Max Activating Token Index: 932

Text #1

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1405584 (Python Code)

Max Activating Token Index: 730

Text #2

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1416735 (Python Code)

Max Activating Token Index: 204

Text #3

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5103. Min Act: -0.0000

Data Index: 1603814 (Python Code)

Max Activating Token Index: 540

Text #4

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5733. Min Act: -0.0000

Data Index: 1640094 (Python Code)

Max Activating Token Index: 709

Text #5

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1557896 (Python Code)

Max Activating Token Index: 719

Text #6

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5044. Min Act: -0.0000

Data Index: 1456822 (Python Code)

Max Activating Token Index: 215

Text #7

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1411974 (Python Code)

Max Activating Token Index: 595

Text #8

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4624. Min Act: -0.0000

Data Index: 1402690 (Python Code)

Max Activating Token Index: 721

Text #9

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.5054. Min Act: -0.0000

Data Index: 1627996 (Python Code)

Max Activating Token Index: 537

Text #10

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4495. Min Act: -0.0000

Data Index: 1503551 (Python Code)

Max Activating Token Index: 958

Text #11

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1501442 (Python Code)

Max Activating Token Index: 744

Text #12

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1431207 (Python Code)

Max Activating Token Index: 627

Text #13

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4842. Min Act: -0.0000

Data Index: 1539643 (Python Code)

Max Activating Token Index: 169

Text #14

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4416. Min Act: -0.0000

Data Index: 1420562 (Python Code)

Max Activating Token Index: 992

Text #15

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4474. Min Act: -0.0000

Data Index: 1610641 (Python Code)

Max Activating Token Index: 294

Text #16

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4297. Min Act: -0.0000

Data Index: 1652674 (Python Code)

Max Activating Token Index: 639

Text #17

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4925. Min Act: -0.0000

Data Index: 1504632 (Python Code)

Max Activating Token Index: 766

Text #18

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4445. Min Act: -0.0000

Data Index: 1465572 (Python Code)

Max Activating Token Index: 748

Text #19

Max Range: 0.7038. Min Range: -0.7038

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1377121 (Python Code)

Max Activating Token Index: 220