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

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

Neuron 5673 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0964. Min Range: -1.0964

Max Act: 1.0964. Min Act: -0.0000

Data Index: 1112126 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 1.0964. Min Range: -1.0964

Max Act: 1.0000. Min Act: -0.0000

Data Index: 961007 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9787. Min Act: -0.0000

Data Index: 993150 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 1.0964. Min Range: -1.0964

Max Act: 1.0065. Min Act: -0.0000

Data Index: 347076 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.9786. Min Act: -0.0000

Data Index: 378159 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.8509. Min Act: -0.0000

Data Index: 404510 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.8895. Min Act: -0.0000

Data Index: 1166567 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.7738. Min Act: -0.0000

Data Index: 616780 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.8789. Min Act: -0.0000

Data Index: 470616 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.8755. Min Act: -0.0000

Data Index: 1307803 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.8493. Min Act: -0.0000

Data Index: 509966 (C4 (Web Text))

Max Activating Token Index: 298

Text #11

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1349385 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.8047. Min Act: -0.0000

Data Index: 100499 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.7486. Min Act: -0.0000

Data Index: 807911 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.7895. Min Act: -0.0000

Data Index: 309014 (C4 (Web Text))

Max Activating Token Index: 271

Text #15

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.8045. Min Act: -0.0000

Data Index: 687322 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.7612. Min Act: -0.0000

Data Index: 271310 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.7131. Min Act: -0.0000

Data Index: 844723 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.7550. Min Act: -0.0000

Data Index: 1101128 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 1.0964. Min Range: -1.0964

Max Act: 0.7329. Min Act: -0.0000

Data Index: 256372 (C4 (Web Text))

Max Activating Token Index: 697