Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1751 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.1049. Min Act: -0.0002

Data Index: 349843 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.1054. Min Act: -0.0001

Data Index: 404194 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0969. Min Act: -0.0002

Data Index: 607392 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0955. Min Act: -0.0001

Data Index: 1218642 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0910. Min Act: -0.0001

Data Index: 29127 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0924. Min Act: -0.0002

Data Index: 191284 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0919. Min Act: -0.0001

Data Index: 124915 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0908. Min Act: -0.0001

Data Index: 928367 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0900. Min Act: -0.0002

Data Index: 153740 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0893. Min Act: -0.0002

Data Index: 50673 (C4 (Web Text))

Max Activating Token Index: 383

Text #10

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0913. Min Act: -0.0002

Data Index: 964211 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0874. Min Act: -0.0002

Data Index: 972895 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0880. Min Act: -0.0002

Data Index: 140137 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0860. Min Act: -0.0002

Data Index: 204231 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0860. Min Act: -0.0001

Data Index: 1279420 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0806. Min Act: -0.0002

Data Index: 156187 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0847. Min Act: -0.0002

Data Index: 862573 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0876. Min Act: -0.0002

Data Index: 49709 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0835. Min Act: -0.0001

Data Index: 887515 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1060270 (C4 (Web Text))

Max Activating Token Index: 695