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

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

Neuron 4038 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.9746. Min Act: -0.0000

Data Index: 1566256 (Python Code)

Max Activating Token Index: 689

Text #1

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.9706. Min Act: -0.0000

Data Index: 1652951 (Python Code)

Max Activating Token Index: 923

Text #2

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.9564. Min Act: -0.0000

Data Index: 1399875 (Python Code)

Max Activating Token Index: 464

Text #3

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.8285. Min Act: -0.0000

Data Index: 1637110 (Python Code)

Max Activating Token Index: 287

Text #4

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.8527. Min Act: -0.0000

Data Index: 1389123 (Python Code)

Max Activating Token Index: 431

Text #5

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.9001. Min Act: -0.0000

Data Index: 1613096 (Python Code)

Max Activating Token Index: 25

Text #6

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.8672. Min Act: -0.0000

Data Index: 1406916 (Python Code)

Max Activating Token Index: 750

Text #7

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.7938. Min Act: -0.0000

Data Index: 1505631 (Python Code)

Max Activating Token Index: 150

Text #8

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.7266. Min Act: -0.0000

Data Index: 1621959 (Python Code)

Max Activating Token Index: 989

Text #9

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.7658. Min Act: -0.0000

Data Index: 1465638 (Python Code)

Max Activating Token Index: 814

Text #10

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.7678. Min Act: -0.0000

Data Index: 1470301 (Python Code)

Max Activating Token Index: 218

Text #11

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.7844. Min Act: -0.0000

Data Index: 1435112 (Python Code)

Max Activating Token Index: 326

Text #12

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.7343. Min Act: -0.0000

Data Index: 1121744 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.7502. Min Act: -0.0000

Data Index: 633451 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1432784 (Python Code)

Max Activating Token Index: 648

Text #15

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.6827. Min Act: -0.0000

Data Index: 1489760 (Python Code)

Max Activating Token Index: 143

Text #16

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.6721. Min Act: -0.0000

Data Index: 336584 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.6900. Min Act: -0.0000

Data Index: 622602 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.7151. Min Act: -0.0000

Data Index: 903271 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.9746. Min Range: -0.9746

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1021496 (C4 (Web Text))

Max Activating Token Index: 328