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

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

Neuron 5743 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.8112. Min Act: -0.0000

Data Index: 458263 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.7446. Min Act: -0.0000

Data Index: 1551446 (Python Code)

Max Activating Token Index: 1003

Text #2

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6595. Min Act: -0.0000

Data Index: 368782 (C4 (Web Text))

Max Activating Token Index: 446

Text #3

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6561. Min Act: -0.0000

Data Index: 387158 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6245. Min Act: -0.0000

Data Index: 516879 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6598. Min Act: -0.0000

Data Index: 473440 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6125. Min Act: -0.0000

Data Index: 253068 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6295. Min Act: -0.0000

Data Index: 150602 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6163. Min Act: -0.0000

Data Index: 1295427 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.6224. Min Act: -0.0000

Data Index: 1259803 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5803. Min Act: -0.0000

Data Index: 246039 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5611. Min Act: -0.0000

Data Index: 899023 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5687. Min Act: -0.0000

Data Index: 486485 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5733. Min Act: -0.0000

Data Index: 1544027 (Python Code)

Max Activating Token Index: 188

Text #14

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5537. Min Act: -0.0000

Data Index: 545066 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5460. Min Act: -0.0000

Data Index: 469589 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5430. Min Act: -0.0000

Data Index: 978021 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5824. Min Act: -0.0000

Data Index: 263442 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1131748 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.8112. Min Range: -0.8112

Max Act: 0.5791. Min Act: -0.0000

Data Index: 1322852 (C4 (Web Text))

Max Activating Token Index: 142