Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1909 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.6498. Min Act: -0.0002

Data Index: 640345 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5870. Min Act: -0.0001

Data Index: 1235742 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.6060. Min Act: -0.0001

Data Index: 1399255 (Python Code)

Max Activating Token Index: 207

Text #3

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5844. Min Act: -0.0002

Data Index: 1285631 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5766. Min Act: -0.0002

Data Index: 1125673 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5533. Min Act: -0.0001

Data Index: 160699 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5060. Min Act: -0.0001

Data Index: 1354649 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5184. Min Act: -0.0002

Data Index: 115599 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4937. Min Act: -0.0001

Data Index: 627256 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5002. Min Act: -0.0001

Data Index: 584552 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5162. Min Act: -0.0001

Data Index: 1187967 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4820. Min Act: -0.0001

Data Index: 688872 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.5106. Min Act: -0.0001

Data Index: 525121 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4828. Min Act: -0.0001

Data Index: 1370065 (Python Code)

Max Activating Token Index: 583

Text #14

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4986. Min Act: -0.0001

Data Index: 111366 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4618. Min Act: -0.0001

Data Index: 1474036 (Python Code)

Max Activating Token Index: 39

Text #16

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4745. Min Act: -0.0002

Data Index: 965665 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4886. Min Act: -0.0001

Data Index: 1388927 (Python Code)

Max Activating Token Index: 462

Text #18

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4826. Min Act: -0.0001

Data Index: 1180689 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.6498. Min Range: -0.6498

Max Act: 0.4651. Min Act: -0.0001

Data Index: 635307 (C4 (Web Text))

Max Activating Token Index: 530