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

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

Neuron 4826 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: 2.1417. Min Range: -2.1417

Max Act: 2.1417. Min Act: -0.0000

Data Index: 659071 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 2.1417. Min Range: -2.1417

Max Act: 1.8583. Min Act: -0.0000

Data Index: 1240977 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 2.1417. Min Range: -2.1417

Max Act: 1.7264. Min Act: -0.0000

Data Index: 859220 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 2.1417. Min Range: -2.1417

Max Act: 1.6977. Min Act: -0.0000

Data Index: 995884 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 2.1417. Min Range: -2.1417

Max Act: 1.7277. Min Act: -0.0000

Data Index: 96723 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 2.1417. Min Range: -2.1417

Max Act: 1.6445. Min Act: -0.0000

Data Index: 371854 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 2.1417. Min Range: -2.1417

Max Act: 1.9027. Min Act: -0.0000

Data Index: 767704 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 2.1417. Min Range: -2.1417

Max Act: 1.6670. Min Act: -0.0000

Data Index: 140110 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 2.1417. Min Range: -2.1417

Max Act: 1.5854. Min Act: -0.0000

Data Index: 794633 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 2.1417. Min Range: -2.1417

Max Act: 1.5876. Min Act: -0.0000

Data Index: 1007899 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 2.1417. Min Range: -2.1417

Max Act: 1.5772. Min Act: -0.0000

Data Index: 614073 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 2.1417. Min Range: -2.1417

Max Act: 1.5794. Min Act: -0.0000

Data Index: 357187 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 2.1417. Min Range: -2.1417

Max Act: 1.5663. Min Act: -0.0000

Data Index: 801962 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 2.1417. Min Range: -2.1417

Max Act: 1.4781. Min Act: -0.0000

Data Index: 214984 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 2.1417. Min Range: -2.1417

Max Act: 1.4896. Min Act: -0.0000

Data Index: 490125 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 2.1417. Min Range: -2.1417

Max Act: 1.5535. Min Act: -0.0000

Data Index: 495043 (C4 (Web Text))

Max Activating Token Index: 514

Text #16

Max Range: 2.1417. Min Range: -2.1417

Max Act: 1.5363. Min Act: -0.0000

Data Index: 867792 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 2.1417. Min Range: -2.1417

Max Act: 1.5558. Min Act: -0.0000

Data Index: 341274 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 2.1417. Min Range: -2.1417

Max Act: 1.5248. Min Act: -0.0000

Data Index: 1049667 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 2.1417. Min Range: -2.1417

Max Act: 1.4100. Min Act: -0.0000

Data Index: 349658 (C4 (Web Text))

Max Activating Token Index: 743