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

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

Neuron 1575 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: 0.1044. Min Range: -0.1044

Max Act: 0.1044. Min Act: -0.0002

Data Index: 1484289 (Python Code)

Max Activating Token Index: 666

Text #1

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0955. Min Act: -0.0002

Data Index: 225234 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0949. Min Act: -0.0002

Data Index: 510312 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0931. Min Act: -0.0002

Data Index: 1232208 (C4 (Web Text))

Max Activating Token Index: 316

Text #4

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0905. Min Act: -0.0002

Data Index: 503801 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0901. Min Act: -0.0002

Data Index: 1082870 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1572348 (Python Code)

Max Activating Token Index: 368

Text #7

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0901. Min Act: -0.0002

Data Index: 933735 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0952. Min Act: -0.0002

Data Index: 1460360 (Python Code)

Max Activating Token Index: 645

Text #9

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0821. Min Act: -0.0002

Data Index: 1583900 (Python Code)

Max Activating Token Index: 653

Text #10

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0891. Min Act: -0.0002

Data Index: 1553504 (Python Code)

Max Activating Token Index: 428

Text #11

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1417386 (Python Code)

Max Activating Token Index: 541

Text #12

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0863. Min Act: -0.0002

Data Index: 1477325 (Python Code)

Max Activating Token Index: 469

Text #13

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0887. Min Act: -0.0002

Data Index: 1450254 (Python Code)

Max Activating Token Index: 256

Text #14

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0832. Min Act: -0.0002

Data Index: 1363861 (Python Code)

Max Activating Token Index: 685

Text #15

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1524372 (Python Code)

Max Activating Token Index: 488

Text #16

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0858. Min Act: -0.0002

Data Index: 1429581 (Python Code)

Max Activating Token Index: 693

Text #17

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0877. Min Act: -0.0002

Data Index: 1408429 (Python Code)

Max Activating Token Index: 979

Text #18

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0894. Min Act: -0.0002

Data Index: 1532089 (Python Code)

Max Activating Token Index: 545

Text #19

Max Range: 0.1044. Min Range: -0.1044

Max Act: 0.0829. Min Act: -0.0002

Data Index: 1404552 (Python Code)

Max Activating Token Index: 658