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

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

Neuron 3984 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3823. Min Range: -5.3823

Max Act: 5.3823. Min Act: -0.0000

Data Index: 391432 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 5.3823. Min Range: -5.3823

Max Act: 5.1495. Min Act: -0.0000

Data Index: 958920 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 5.3823. Min Range: -5.3823

Max Act: 4.8067. Min Act: -0.0000

Data Index: 720753 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 5.3823. Min Range: -5.3823

Max Act: 4.6568. Min Act: -0.0000

Data Index: 646814 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 5.3823. Min Range: -5.3823

Max Act: 4.9350. Min Act: -0.0000

Data Index: 364525 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 5.3823. Min Range: -5.3823

Max Act: 4.5322. Min Act: -0.0000

Data Index: 651504 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 5.3823. Min Range: -5.3823

Max Act: 4.1340. Min Act: -0.0000

Data Index: 706558 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 5.3823. Min Range: -5.3823

Max Act: 4.6257. Min Act: -0.0000

Data Index: 1132358 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 5.3823. Min Range: -5.3823

Max Act: 4.5598. Min Act: -0.0000

Data Index: 247564 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 5.3823. Min Range: -5.3823

Max Act: 4.5438. Min Act: -0.0000

Data Index: 312153 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 5.3823. Min Range: -5.3823

Max Act: 4.5020. Min Act: -0.0000

Data Index: 1046773 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 5.3823. Min Range: -5.3823

Max Act: 4.1486. Min Act: -0.0000

Data Index: 459913 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 5.3823. Min Range: -5.3823

Max Act: 4.1077. Min Act: -0.0000

Data Index: 750741 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 5.3823. Min Range: -5.3823

Max Act: 4.2670. Min Act: -0.0000

Data Index: 1308997 (C4 (Web Text))

Max Activating Token Index: 885

Text #14

Max Range: 5.3823. Min Range: -5.3823

Max Act: 4.0797. Min Act: -0.0000

Data Index: 1150590 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 5.3823. Min Range: -5.3823

Max Act: 4.1715. Min Act: -0.0000

Data Index: 932887 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 5.3823. Min Range: -5.3823

Max Act: 4.0753. Min Act: -0.0000

Data Index: 523309 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 5.3823. Min Range: -5.3823

Max Act: 4.1049. Min Act: -0.0000

Data Index: 355555 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 5.3823. Min Range: -5.3823

Max Act: 3.8530. Min Act: -0.0000

Data Index: 741348 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 5.3823. Min Range: -5.3823

Max Act: 3.8218. Min Act: -0.0000

Data Index: 277298 (C4 (Web Text))

Max Activating Token Index: 560