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

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

Neuron 1275 in Layer 1

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: 0.2073. Min Range: -0.2073

Max Act: 0.2073. Min Act: -0.0002

Data Index: 1034714 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1292. Min Act: -0.0002

Data Index: 322494 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1175. Min Act: -0.0002

Data Index: 38555 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1080. Min Act: -0.0002

Data Index: 1108118 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1073. Min Act: -0.0002

Data Index: 954564 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1065. Min Act: -0.0002

Data Index: 725471 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1029. Min Act: -0.0002

Data Index: 868786 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1025. Min Act: -0.0002

Data Index: 761912 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1034. Min Act: -0.0002

Data Index: 936184 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.0986. Min Act: -0.0002

Data Index: 99748 (C4 (Web Text))

Max Activating Token Index: 586

Text #10

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.1002. Min Act: -0.0002

Data Index: 462809 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.0957. Min Act: -0.0002

Data Index: 593468 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.0932. Min Act: -0.0002

Data Index: 626563 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.0925. Min Act: -0.0002

Data Index: 40303 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.0903. Min Act: -0.0002

Data Index: 1113432 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.0910. Min Act: -0.0002

Data Index: 534720 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.0894. Min Act: -0.0002

Data Index: 497461 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.0889. Min Act: -0.0003

Data Index: 564235 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.0874. Min Act: -0.0002

Data Index: 374299 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.2073. Min Range: -0.2073

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1138472 (C4 (Web Text))

Max Activating Token Index: 174