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

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

Neuron 6091 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0663. Min Range: -1.0663

Max Act: 1.0663. Min Act: -0.0002

Data Index: 1529385 (Python Code)

Max Activating Token Index: 889

Text #1

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.7563. Min Act: -0.0002

Data Index: 837129 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.6648. Min Act: -0.0002

Data Index: 1121134 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.4437. Min Act: -0.0002

Data Index: 940843 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.3618. Min Act: -0.0002

Data Index: 1591930 (Python Code)

Max Activating Token Index: 896

Text #5

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.3301. Min Act: -0.0002

Data Index: 1233715 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.3450. Min Act: -0.0002

Data Index: 635401 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.3555. Min Act: -0.0002

Data Index: 1322862 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.2932. Min Act: -0.0002

Data Index: 950698 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.2971. Min Act: -0.0002

Data Index: 555893 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.2288. Min Act: -0.0002

Data Index: 607280 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.1815. Min Act: -0.0002

Data Index: 1139484 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.2060. Min Act: -0.0002

Data Index: 840380 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.1908. Min Act: -0.0002

Data Index: 1273998 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.1579. Min Act: -0.0002

Data Index: 807900 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.1800. Min Act: -0.0002

Data Index: 741234 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.1659. Min Act: -0.0002

Data Index: 1141712 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.1572. Min Act: -0.0002

Data Index: 1047943 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.1311. Min Act: -0.0002

Data Index: 957642 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 1.0663. Min Range: -1.0663

Max Act: 0.1576. Min Act: -0.0002

Data Index: 1326609 (C4 (Web Text))

Max Activating Token Index: 1023