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

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

Neuron 4252 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0637. Min Act: -0.0002

Data Index: 1064481 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0566. Min Act: -0.0002

Data Index: 886963 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0592. Min Act: -0.0002

Data Index: 490233 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0556. Min Act: -0.0002

Data Index: 59165 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0564. Min Act: -0.0001

Data Index: 979171 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0546. Min Act: -0.0002

Data Index: 821680 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1036288 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0570. Min Act: -0.0002

Data Index: 517146 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0541. Min Act: -0.0002

Data Index: 727831 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0539. Min Act: -0.0002

Data Index: 428267 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1072244 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0532. Min Act: -0.0002

Data Index: 880828 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0533. Min Act: -0.0002

Data Index: 651273 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0514. Min Act: -0.0002

Data Index: 200505 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0531. Min Act: -0.0002

Data Index: 143736 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0509. Min Act: -0.0002

Data Index: 742034 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0507. Min Act: -0.0002

Data Index: 995226 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1130408 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0525. Min Act: -0.0002

Data Index: 855264 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0517. Min Act: -0.0002

Data Index: 846445 (C4 (Web Text))

Max Activating Token Index: 952