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

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

Neuron 262 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: 0.3100. Min Range: -0.3100

Max Act: 0.3100. Min Act: -0.0001

Data Index: 1554703 (Python Code)

Max Activating Token Index: 852

Text #1

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2996. Min Act: -0.0001

Data Index: 1439448 (Python Code)

Max Activating Token Index: 944

Text #2

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2978. Min Act: -0.0001

Data Index: 1420786 (Python Code)

Max Activating Token Index: 116

Text #3

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2917. Min Act: -0.0002

Data Index: 1593703 (Python Code)

Max Activating Token Index: 124

Text #4

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2931. Min Act: -0.0002

Data Index: 1476812 (Python Code)

Max Activating Token Index: 389

Text #5

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2880. Min Act: -0.0001

Data Index: 1493067 (Python Code)

Max Activating Token Index: 196

Text #6

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2856. Min Act: -0.0001

Data Index: 1505227 (Python Code)

Max Activating Token Index: 20

Text #7

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2902. Min Act: -0.0001

Data Index: 1645912 (Python Code)

Max Activating Token Index: 281

Text #8

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2861. Min Act: -0.0001

Data Index: 1594101 (Python Code)

Max Activating Token Index: 474

Text #9

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2820. Min Act: -0.0001

Data Index: 1363921 (Python Code)

Max Activating Token Index: 212

Text #10

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2826. Min Act: -0.0001

Data Index: 1523652 (Python Code)

Max Activating Token Index: 846

Text #11

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2865. Min Act: -0.0001

Data Index: 1635867 (Python Code)

Max Activating Token Index: 710

Text #12

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2769. Min Act: -0.0001

Data Index: 1434171 (Python Code)

Max Activating Token Index: 992

Text #13

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2732. Min Act: -0.0001

Data Index: 1521870 (Python Code)

Max Activating Token Index: 33

Text #14

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2704. Min Act: -0.0001

Data Index: 1534103 (Python Code)

Max Activating Token Index: 512

Text #15

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2744. Min Act: -0.0001

Data Index: 1597992 (Python Code)

Max Activating Token Index: 161

Text #16

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2767. Min Act: -0.0001

Data Index: 1638657 (Python Code)

Max Activating Token Index: 77

Text #17

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2755. Min Act: -0.0001

Data Index: 1567785 (Python Code)

Max Activating Token Index: 532

Text #18

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2741. Min Act: -0.0001

Data Index: 1556407 (Python Code)

Max Activating Token Index: 29

Text #19

Max Range: 0.3100. Min Range: -0.3100

Max Act: 0.2707. Min Act: -0.0001

Data Index: 1598614 (Python Code)

Max Activating Token Index: 66