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

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

Neuron 868 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.6610. Min Act: -0.0000

Data Index: 551729 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.6485. Min Act: -0.0001

Data Index: 565521 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5605. Min Act: -0.0000

Data Index: 179383 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5379. Min Act: 0.0000

Data Index: 304819 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5592. Min Act: -0.0000

Data Index: 390908 (C4 (Web Text))

Max Activating Token Index: 828

Text #5

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5209. Min Act: 0.0001

Data Index: 726917 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.5240. Min Act: 0.0000

Data Index: 340619 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4778. Min Act: -0.0000

Data Index: 541627 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4958. Min Act: -0.0000

Data Index: 1217865 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4766. Min Act: -0.0000

Data Index: 888070 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4615. Min Act: -0.0000

Data Index: 369238 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4890. Min Act: -0.0000

Data Index: 622170 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4730. Min Act: -0.0000

Data Index: 1176425 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4784. Min Act: -0.0000

Data Index: 20086 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4636. Min Act: -0.0000

Data Index: 57849 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4707. Min Act: 0.0000

Data Index: 1080564 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4841. Min Act: -0.0000

Data Index: 864107 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4782. Min Act: 0.0000

Data Index: 274996 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4633. Min Act: -0.0000

Data Index: 194291 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.6610. Min Range: -0.6610

Max Act: 0.4766. Min Act: -0.0000

Data Index: 1260364 (C4 (Web Text))

Max Activating Token Index: 168