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

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

Neuron 732 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: 0.1025. Min Range: -0.1025

Max Act: 0.1025. Min Act: -0.0002

Data Index: 1446251 (Python Code)

Max Activating Token Index: 433

Text #1

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0989. Min Act: -0.0002

Data Index: 1501749 (Python Code)

Max Activating Token Index: 576

Text #2

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0983. Min Act: -0.0002

Data Index: 1416420 (Python Code)

Max Activating Token Index: 139

Text #3

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0971. Min Act: -0.0002

Data Index: 1625253 (Python Code)

Max Activating Token Index: 183

Text #4

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0972. Min Act: -0.0002

Data Index: 1473637 (Python Code)

Max Activating Token Index: 550

Text #5

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0941. Min Act: -0.0002

Data Index: 1451159 (Python Code)

Max Activating Token Index: 495

Text #6

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0950. Min Act: -0.0002

Data Index: 1505437 (Python Code)

Max Activating Token Index: 878

Text #7

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0949. Min Act: -0.0002

Data Index: 1591386 (Python Code)

Max Activating Token Index: 589

Text #8

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1654613 (Python Code)

Max Activating Token Index: 117

Text #9

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0912. Min Act: -0.0002

Data Index: 1505429 (Python Code)

Max Activating Token Index: 850

Text #10

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0916. Min Act: -0.0002

Data Index: 1430678 (Python Code)

Max Activating Token Index: 803

Text #11

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0913. Min Act: -0.0002

Data Index: 1505189 (Python Code)

Max Activating Token Index: 430

Text #12

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0894. Min Act: -0.0002

Data Index: 1400363 (Python Code)

Max Activating Token Index: 498

Text #13

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0920. Min Act: -0.0002

Data Index: 1404761 (Python Code)

Max Activating Token Index: 353

Text #14

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0892. Min Act: -0.0002

Data Index: 1395317 (Python Code)

Max Activating Token Index: 638

Text #15

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0876. Min Act: -0.0002

Data Index: 1386672 (Python Code)

Max Activating Token Index: 506

Text #16

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0883. Min Act: -0.0002

Data Index: 1403897 (Python Code)

Max Activating Token Index: 813

Text #17

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0899. Min Act: -0.0002

Data Index: 1435069 (Python Code)

Max Activating Token Index: 768

Text #18

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0890. Min Act: -0.0002

Data Index: 1580376 (Python Code)

Max Activating Token Index: 95

Text #19

Max Range: 0.1025. Min Range: -0.1025

Max Act: 0.0891. Min Act: -0.0002

Data Index: 1527349 (Python Code)

Max Activating Token Index: 1005