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

Dataset: The Pile

Neuron 2221 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.6868. Min Act: -0.0000

Data Index: 354886 (The Pile)

Max Activating Token Index: 661

Text #1

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.6494. Min Act: -0.0000

Data Index: 875351 (The Pile)

Max Activating Token Index: 180

Text #2

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.6276. Min Act: -0.0000

Data Index: 914529 (The Pile)

Max Activating Token Index: 26

Text #3

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1246704 (The Pile)

Max Activating Token Index: 176

Text #4

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.6251. Min Act: 0.0000

Data Index: 1414127 (The Pile)

Max Activating Token Index: 505

Text #5

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1561358 (The Pile)

Max Activating Token Index: 437

Text #6

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.5908. Min Act: -0.0000

Data Index: 793682 (The Pile)

Max Activating Token Index: 558

Text #7

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1672298 (The Pile)

Max Activating Token Index: 607

Text #8

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.4896. Min Act: -0.0000

Data Index: 882347 (The Pile)

Max Activating Token Index: 53

Text #9

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.4956. Min Act: -0.0000

Data Index: 67772 (The Pile)

Max Activating Token Index: 368

Text #10

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.5031. Min Act: -0.0000

Data Index: 755819 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.4831. Min Act: -0.0000

Data Index: 390857 (The Pile)

Max Activating Token Index: 939

Text #12

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.4958. Min Act: -0.0000

Data Index: 1337717 (The Pile)

Max Activating Token Index: 543

Text #13

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1902677 (The Pile)

Max Activating Token Index: 44

Text #14

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.4959. Min Act: -0.0000

Data Index: 468408 (The Pile)

Max Activating Token Index: 822

Text #15

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.4863. Min Act: -0.0000

Data Index: 807977 (The Pile)

Max Activating Token Index: 205

Text #16

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.4470. Min Act: -0.0000

Data Index: 1256356 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.4556. Min Act: -0.0000

Data Index: 1224253 (The Pile)

Max Activating Token Index: 1014

Text #18

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.4294. Min Act: 0.0000

Data Index: 1080614 (The Pile)

Max Activating Token Index: 176

Text #19

Max Range: 0.6868. Min Range: -0.6868

Max Act: 0.4529. Min Act: -0.0000

Data Index: 1114213 (The Pile)

Max Activating Token Index: 369