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

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

Neuron 5446 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.5889. Min Act: -0.0000

Data Index: 403159 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.4153. Min Act: -0.0000

Data Index: 488796 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.2491. Min Act: -0.0000

Data Index: 624100 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.2437. Min Act: -0.0000

Data Index: 585529 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.1234. Min Act: -0.0000

Data Index: 648019 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.1755. Min Act: -0.0000

Data Index: 568387 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.1786. Min Act: -0.0000

Data Index: 894122 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.0346. Min Act: -0.0000

Data Index: 584033 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.0674. Min Act: 0.0000

Data Index: 1016622 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.0603. Min Act: -0.0000

Data Index: 219861 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.0574. Min Act: -0.0000

Data Index: 888388 (C4 (Web Text))

Max Activating Token Index: 66

Text #11

Max Range: 1.5889. Min Range: -1.5889

Max Act: 0.9919. Min Act: -0.0000

Data Index: 1009679 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.0398. Min Act: -0.0000

Data Index: 537848 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.0367. Min Act: 0.0000

Data Index: 862980 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.0161. Min Act: -0.0000

Data Index: 1245398 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.0762. Min Act: -0.0000

Data Index: 70082 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.0166. Min Act: -0.0000

Data Index: 500755 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.0144. Min Act: -0.0000

Data Index: 1124572 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.0770. Min Act: -0.0000

Data Index: 164115 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 1.5889. Min Range: -1.5889

Max Act: 1.0010. Min Act: -0.0000

Data Index: 644598 (C4 (Web Text))

Max Activating Token Index: 537