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

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

Neuron 4280 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.9280. Min Act: -0.0000

Data Index: 99908 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.8647. Min Act: -0.0000

Data Index: 98196 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.9082. Min Act: -0.0000

Data Index: 264390 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.7317. Min Act: -0.0000

Data Index: 920043 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.7483. Min Act: -0.0000

Data Index: 470973 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.6756. Min Act: -0.0000

Data Index: 209340 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.6940. Min Act: -0.0000

Data Index: 924900 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.6843. Min Act: -0.0000

Data Index: 255564 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.6987. Min Act: -0.0000

Data Index: 1153850 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.6564. Min Act: -0.0000

Data Index: 365290 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.6748. Min Act: -0.0000

Data Index: 525622 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.6754. Min Act: -0.0000

Data Index: 768341 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.6680. Min Act: -0.0000

Data Index: 1103110 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.6483. Min Act: -0.0000

Data Index: 80458 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.6654. Min Act: -0.0000

Data Index: 575818 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1141493 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.6427. Min Act: -0.0000

Data Index: 149873 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.6258. Min Act: -0.0000

Data Index: 457502 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.6416. Min Act: -0.0000

Data Index: 636554 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 0.9280. Min Range: -0.9280

Max Act: 0.6370. Min Act: -0.0000

Data Index: 1001672 (C4 (Web Text))

Max Activating Token Index: 716