Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 113 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1588708 (Python Code)

Max Activating Token Index: 614

Text #1

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0949. Min Act: -0.0001

Data Index: 653536 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1437410 (Python Code)

Max Activating Token Index: 131

Text #3

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0851. Min Act: -0.0002

Data Index: 1385515 (Python Code)

Max Activating Token Index: 259

Text #4

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0860. Min Act: -0.0002

Data Index: 1602703 (Python Code)

Max Activating Token Index: 934

Text #5

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0919. Min Act: -0.0002

Data Index: 426058 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0861. Min Act: -0.0002

Data Index: 37384 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0904. Min Act: -0.0001

Data Index: 1015011 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0866. Min Act: -0.0002

Data Index: 1111575 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0886. Min Act: -0.0001

Data Index: 868580 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0866. Min Act: -0.0002

Data Index: 840544 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0827. Min Act: -0.0001

Data Index: 933017 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0877. Min Act: -0.0001

Data Index: 1555500 (Python Code)

Max Activating Token Index: 903

Text #13

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1642986 (Python Code)

Max Activating Token Index: 419

Text #14

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0849. Min Act: -0.0002

Data Index: 673207 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0838. Min Act: -0.0002

Data Index: 1563251 (Python Code)

Max Activating Token Index: 854

Text #16

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1467250 (Python Code)

Max Activating Token Index: 394

Text #17

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0864. Min Act: -0.0002

Data Index: 1468755 (Python Code)

Max Activating Token Index: 396

Text #18

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1475056 (Python Code)

Max Activating Token Index: 144

Text #19

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0812. Min Act: -0.0002

Data Index: 1523193 (Python Code)

Max Activating Token Index: 1019