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

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

Neuron 1087 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: 0.0928. Min Range: -0.0928

Max Act: 0.0915. Min Act: -0.0001

Data Index: 259188 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0928. Min Act: -0.0001

Data Index: 1278249 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0896. Min Act: -0.0001

Data Index: 675673 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0827. Min Act: -0.0001

Data Index: 857536 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0814. Min Act: -0.0001

Data Index: 891379 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0813. Min Act: -0.0001

Data Index: 1227290 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0803. Min Act: -0.0001

Data Index: 377633 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0817. Min Act: -0.0001

Data Index: 53265 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0774. Min Act: -0.0001

Data Index: 557651 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0785. Min Act: -0.0001

Data Index: 1320639 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0790. Min Act: -0.0001

Data Index: 31928 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0758. Min Act: -0.0001

Data Index: 520125 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0769. Min Act: -0.0001

Data Index: 651540 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0761. Min Act: -0.0001

Data Index: 470997 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0761. Min Act: -0.0001

Data Index: 1255122 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0765. Min Act: -0.0001

Data Index: 270243 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0746. Min Act: -0.0001

Data Index: 492955 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0753. Min Act: -0.0001

Data Index: 1109828 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0744. Min Act: -0.0001

Data Index: 93455 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 0.0928. Min Range: -0.0928

Max Act: 0.0752. Min Act: -0.0001

Data Index: 844710 (C4 (Web Text))

Max Activating Token Index: 307