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

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

Neuron 881 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.4967. Min Act: -0.0001

Data Index: 45614 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 3.4967. Min Range: -3.4967

Max Act: 3.0976. Min Act: -0.0000

Data Index: 1215319 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.3708. Min Act: -0.0001

Data Index: 1005501 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.7141. Min Act: -0.0000

Data Index: 727396 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.5811. Min Act: -0.0001

Data Index: 567292 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.7236. Min Act: -0.0001

Data Index: 432465 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.7119. Min Act: -0.0001

Data Index: 823091 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.5603. Min Act: -0.0001

Data Index: 477874 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.6195. Min Act: -0.0001

Data Index: 1001629 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.5454. Min Act: -0.0001

Data Index: 795350 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.3652. Min Act: -0.0001

Data Index: 985273 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.5685. Min Act: -0.0000

Data Index: 560745 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.4486. Min Act: -0.0001

Data Index: 198232 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.5633. Min Act: -0.0001

Data Index: 460456 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.4981. Min Act: -0.0001

Data Index: 274108 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.4901. Min Act: -0.0001

Data Index: 569386 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.2396. Min Act: -0.0001

Data Index: 648612 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.0264. Min Act: -0.0001

Data Index: 547973 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.3673. Min Act: -0.0000

Data Index: 587868 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 3.4967. Min Range: -3.4967

Max Act: 2.2355. Min Act: -0.0001

Data Index: 356844 (C4 (Web Text))

Max Activating Token Index: 365