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

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

Neuron 1425 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: 0.5008. Min Range: -0.5008

Max Act: 0.5008. Min Act: -0.0001

Data Index: 78447 (C4 (Web Text))

Max Activating Token Index: 543

Text #1

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4886. Min Act: -0.0000

Data Index: 325838 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4627. Min Act: -0.0000

Data Index: 190671 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4839. Min Act: -0.0000

Data Index: 945454 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4479. Min Act: -0.0001

Data Index: 478910 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1091422 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4594. Min Act: -0.0000

Data Index: 578366 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4369. Min Act: -0.0001

Data Index: 468320 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4518. Min Act: -0.0000

Data Index: 1202198 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4647. Min Act: -0.0000

Data Index: 618966 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4528. Min Act: -0.0001

Data Index: 388066 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4346. Min Act: -0.0000

Data Index: 473579 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4344. Min Act: -0.0000

Data Index: 445601 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.3910. Min Act: -0.0000

Data Index: 547264 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4297. Min Act: -0.0000

Data Index: 1223579 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4002. Min Act: -0.0000

Data Index: 356424 (C4 (Web Text))

Max Activating Token Index: 642

Text #16

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4049. Min Act: -0.0000

Data Index: 238937 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.4531. Min Act: -0.0000

Data Index: 129034 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.3974. Min Act: -0.0000

Data Index: 881929 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.5008. Min Range: -0.5008

Max Act: 0.3832. Min Act: -0.0001

Data Index: 233142 (C4 (Web Text))

Max Activating Token Index: 145