Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4584 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.7240. Min Act: -0.0000

Data Index: 13464 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.7433. Min Act: -0.0000

Data Index: 319938 (C4 (Web Text))

Max Activating Token Index: 178

Text #2

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.7101. Min Act: -0.0000

Data Index: 1038697 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.6504. Min Act: -0.0000

Data Index: 906805 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.7245. Min Act: -0.0000

Data Index: 732094 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.6767. Min Act: -0.0000

Data Index: 475003 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.6418. Min Act: -0.0000

Data Index: 833501 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.6550. Min Act: -0.0000

Data Index: 969510 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.6094. Min Act: -0.0000

Data Index: 256070 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.6413. Min Act: -0.0000

Data Index: 366128 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.6473. Min Act: -0.0000

Data Index: 309816 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.6235. Min Act: -0.0000

Data Index: 1070565 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.6283. Min Act: -0.0000

Data Index: 1213450 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.6364. Min Act: -0.0000

Data Index: 280691 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.6291. Min Act: -0.0000

Data Index: 264957 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.6096. Min Act: -0.0000

Data Index: 356155 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.6466. Min Act: -0.0000

Data Index: 597968 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.6513. Min Act: -0.0000

Data Index: 611014 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.6375. Min Act: -0.0000

Data Index: 175335 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.7433. Min Range: -0.7433

Max Act: 0.5605. Min Act: -0.0000

Data Index: 1235911 (C4 (Web Text))

Max Activating Token Index: 46