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

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

Neuron 700 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1692. Min Act: -0.0001

Data Index: 590295 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1350. Min Act: -0.0001

Data Index: 409228 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.0960. Min Act: -0.0001

Data Index: 318826 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.0955. Min Act: -0.0001

Data Index: 852639 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.0979. Min Act: -0.0001

Data Index: 752340 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.0917. Min Act: -0.0001

Data Index: 146146 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1015. Min Act: -0.0001

Data Index: 212105 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.0906. Min Act: -0.0001

Data Index: 45552 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1024. Min Act: -0.0001

Data Index: 878390 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.0921. Min Act: -0.0001

Data Index: 56415 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.0889. Min Act: -0.0001

Data Index: 125780 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.0916. Min Act: -0.0001

Data Index: 46143 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.0946. Min Act: -0.0001

Data Index: 63266 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.0940. Min Act: -0.0001

Data Index: 747514 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.0854. Min Act: -0.0001

Data Index: 1302207 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.0875. Min Act: -0.0000

Data Index: 990487 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.0803. Min Act: -0.0001

Data Index: 805740 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.0931. Min Act: -0.0001

Data Index: 254026 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.0817. Min Act: -0.0000

Data Index: 959542 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.0862. Min Act: -0.0001

Data Index: 594070 (C4 (Web Text))

Max Activating Token Index: 35