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

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

Neuron 1498 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8427. Min Range: -0.8427

Max Act: 0.8427. Min Act: -0.0000

Data Index: 7790 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 0.8427. Min Range: -0.8427

Max Act: 0.7491. Min Act: -0.0000

Data Index: 621345 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.8427. Min Range: -0.8427

Max Act: 0.7887. Min Act: -0.0000

Data Index: 494530 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 0.8427. Min Range: -0.8427

Max Act: 0.7795. Min Act: -0.0000

Data Index: 711849 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.8427. Min Range: -0.8427

Max Act: 0.8019. Min Act: -0.0000

Data Index: 347258 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.8427. Min Range: -0.8427

Max Act: 0.8320. Min Act: -0.0000

Data Index: 433935 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.8427. Min Range: -0.8427

Max Act: 0.6981. Min Act: -0.0000

Data Index: 21100 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 0.8427. Min Range: -0.8427

Max Act: 0.6712. Min Act: -0.0000

Data Index: 180015 (C4 (Web Text))

Max Activating Token Index: 673

Text #8

Max Range: 0.8427. Min Range: -0.8427

Max Act: 0.7129. Min Act: -0.0000

Data Index: 1084517 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.8427. Min Range: -0.8427

Max Act: 0.6903. Min Act: -0.0000

Data Index: 1260823 (C4 (Web Text))

Max Activating Token Index: 716

Text #10

Max Range: 0.8427. Min Range: -0.8427

Max Act: 0.7462. Min Act: -0.0000

Data Index: 220433 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 0.8427. Min Range: -0.8427

Max Act: 0.6666. Min Act: -0.0000

Data Index: 596250 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.8427. Min Range: -0.8427

Max Act: 0.5820. Min Act: -0.0000

Data Index: 281494 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.8427. Min Range: -0.8427

Max Act: 0.6997. Min Act: -0.0000

Data Index: 799392 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 0.8427. Min Range: -0.8427

Max Act: 0.6519. Min Act: -0.0000

Data Index: 610069 (C4 (Web Text))

Max Activating Token Index: 485

Text #15

Max Range: 0.8427. Min Range: -0.8427

Max Act: 0.7002. Min Act: -0.0000

Data Index: 387589 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 0.8427. Min Range: -0.8427

Max Act: 0.6549. Min Act: -0.0000

Data Index: 110628 (C4 (Web Text))

Max Activating Token Index: 818

Text #17

Max Range: 0.8427. Min Range: -0.8427

Max Act: 0.6155. Min Act: -0.0000

Data Index: 1137933 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 0.8427. Min Range: -0.8427

Max Act: 0.6752. Min Act: -0.0000

Data Index: 628167 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.8427. Min Range: -0.8427

Max Act: 0.6574. Min Act: -0.0000

Data Index: 505397 (C4 (Web Text))

Max Activating Token Index: 559