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

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

Neuron 2048 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1800. Min Range: -1.1800

Max Act: 1.1800. Min Act: -0.0000

Data Index: 143673 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 1.1800. Min Range: -1.1800

Max Act: 1.0078. Min Act: -0.0000

Data Index: 658197 (C4 (Web Text))

Max Activating Token Index: 230

Text #2

Max Range: 1.1800. Min Range: -1.1800

Max Act: 0.8967. Min Act: -0.0000

Data Index: 31497 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 1.1800. Min Range: -1.1800

Max Act: 0.8499. Min Act: -0.0000

Data Index: 405626 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 1.1800. Min Range: -1.1800

Max Act: 0.8082. Min Act: -0.0000

Data Index: 168922 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 1.1800. Min Range: -1.1800

Max Act: 0.7545. Min Act: -0.0000

Data Index: 627186 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 1.1800. Min Range: -1.1800

Max Act: 0.7797. Min Act: -0.0000

Data Index: 114345 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 1.1800. Min Range: -1.1800

Max Act: 0.7465. Min Act: -0.0000

Data Index: 157850 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 1.1800. Min Range: -1.1800

Max Act: 0.7593. Min Act: -0.0000

Data Index: 792450 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 1.1800. Min Range: -1.1800

Max Act: 0.7087. Min Act: 0.0000

Data Index: 877620 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 1.1800. Min Range: -1.1800

Max Act: 0.7058. Min Act: -0.0000

Data Index: 1267736 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 1.1800. Min Range: -1.1800

Max Act: 0.7010. Min Act: -0.0000

Data Index: 1048775 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 1.1800. Min Range: -1.1800

Max Act: 0.6517. Min Act: -0.0000

Data Index: 483796 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 1.1800. Min Range: -1.1800

Max Act: 0.6847. Min Act: -0.0000

Data Index: 866445 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 1.1800. Min Range: -1.1800

Max Act: 0.6846. Min Act: -0.0000

Data Index: 510785 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 1.1800. Min Range: -1.1800

Max Act: 0.7196. Min Act: -0.0000

Data Index: 971764 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 1.1800. Min Range: -1.1800

Max Act: 0.6553. Min Act: 0.0000

Data Index: 463581 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 1.1800. Min Range: -1.1800

Max Act: 0.6264. Min Act: -0.0000

Data Index: 135866 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 1.1800. Min Range: -1.1800

Max Act: 0.6411. Min Act: -0.0000

Data Index: 469796 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 1.1800. Min Range: -1.1800

Max Act: 0.7030. Min Act: -0.0000

Data Index: 613532 (C4 (Web Text))

Max Activating Token Index: 552