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

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

Neuron 3395 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.3028. Min Act: -0.0001

Data Index: 48112 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2992. Min Act: -0.0001

Data Index: 1600124 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.3018. Min Act: -0.0001

Data Index: 1033331 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2935. Min Act: -0.0001

Data Index: 1592789 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2918. Min Act: -0.0001

Data Index: 726737 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2889. Min Act: -0.0001

Data Index: 1370073 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2871. Min Act: -0.0001

Data Index: 1557885 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2835. Min Act: -0.0001

Data Index: 965901 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2801. Min Act: -0.0001

Data Index: 585626 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2872. Min Act: -0.0001

Data Index: 1052222 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2873. Min Act: -0.0001

Data Index: 1620877 (Python Code)

Max Activating Token Index: 70

Text #11

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2825. Min Act: -0.0001

Data Index: 679951 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2812. Min Act: -0.0001

Data Index: 613411 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2755. Min Act: -0.0001

Data Index: 774609 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2781. Min Act: -0.0001

Data Index: 809286 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2798. Min Act: -0.0001

Data Index: 250530 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2741. Min Act: -0.0001

Data Index: 934465 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2736. Min Act: -0.0001

Data Index: 830657 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2776. Min Act: -0.0001

Data Index: 634754 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 0.3028. Min Range: -0.3028

Max Act: 0.2776. Min Act: -0.0001

Data Index: 478094 (C4 (Web Text))

Max Activating Token Index: 2