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

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

Neuron 4498 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0804. Min Range: -1.0804

Max Act: 1.0804. Min Act: -0.0000

Data Index: 735264 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 1.0804. Min Range: -1.0804

Max Act: 1.0079. Min Act: -0.0000

Data Index: 975323 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 1.0804. Min Range: -1.0804

Max Act: 1.0272. Min Act: -0.0000

Data Index: 68087 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.9696. Min Act: -0.0000

Data Index: 1178744 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.9344. Min Act: -0.0000

Data Index: 637018 (C4 (Web Text))

Max Activating Token Index: 240

Text #5

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.9311. Min Act: -0.0000

Data Index: 1350382 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.9127. Min Act: 0.0001

Data Index: 564177 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.8848. Min Act: -0.0000

Data Index: 842030 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.9660. Min Act: 0.0000

Data Index: 589329 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.9000. Min Act: -0.0000

Data Index: 1044959 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1314162 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.8667. Min Act: -0.0000

Data Index: 85979 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.8625. Min Act: -0.0000

Data Index: 48050 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.8672. Min Act: -0.0000

Data Index: 21910 (C4 (Web Text))

Max Activating Token Index: 753

Text #14

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.9750. Min Act: -0.0000

Data Index: 649273 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.8951. Min Act: -0.0000

Data Index: 534991 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.7973. Min Act: -0.0000

Data Index: 1199719 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.8563. Min Act: -0.0000

Data Index: 574121 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.8653. Min Act: 0.0001

Data Index: 424944 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 1.0804. Min Range: -1.0804

Max Act: 0.7987. Min Act: -0.0000

Data Index: 400964 (C4 (Web Text))

Max Activating Token Index: 888