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

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

Neuron 538 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: 0.1006. Min Range: -0.1006

Max Act: 0.1001. Min Act: -0.0002

Data Index: 1103075 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.1006. Min Act: -0.0001

Data Index: 1232409 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0958. Min Act: -0.0001

Data Index: 1178498 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0923. Min Act: -0.0002

Data Index: 719774 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0936. Min Act: -0.0001

Data Index: 256053 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0933. Min Act: -0.0001

Data Index: 1349382 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0901. Min Act: -0.0001

Data Index: 16876 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0919. Min Act: -0.0001

Data Index: 72957 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0929. Min Act: -0.0001

Data Index: 210392 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1191041 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0893. Min Act: -0.0001

Data Index: 952551 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0898. Min Act: -0.0001

Data Index: 845622 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0896. Min Act: -0.0001

Data Index: 604557 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0909. Min Act: -0.0001

Data Index: 313916 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0888. Min Act: -0.0001

Data Index: 985279 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0905. Min Act: -0.0001

Data Index: 1304495 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0894. Min Act: -0.0001

Data Index: 199916 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0881. Min Act: -0.0001

Data Index: 649642 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0896. Min Act: -0.0001

Data Index: 408750 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 0.1006. Min Range: -0.1006

Max Act: 0.0880. Min Act: -0.0001

Data Index: 951530 (C4 (Web Text))

Max Activating Token Index: 72