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

Dataset: The Pile

Neuron 2642 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.6470. Min Act: -0.0000

Data Index: 1933128 (The Pile)

Max Activating Token Index: 553

Text #1

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.6170. Min Act: -0.0000

Data Index: 269487 (The Pile)

Max Activating Token Index: 499

Text #2

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.5352. Min Act: -0.0000

Data Index: 67050 (The Pile)

Max Activating Token Index: 170

Text #3

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4811. Min Act: -0.0000

Data Index: 239173 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1852980 (The Pile)

Max Activating Token Index: 126

Text #5

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4908. Min Act: -0.0000

Data Index: 914574 (The Pile)

Max Activating Token Index: 564

Text #6

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1065342 (The Pile)

Max Activating Token Index: 210

Text #7

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.5262. Min Act: -0.0000

Data Index: 488388 (The Pile)

Max Activating Token Index: 153

Text #8

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.5006. Min Act: -0.0000

Data Index: 484639 (The Pile)

Max Activating Token Index: 991

Text #9

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4702. Min Act: -0.0000

Data Index: 668448 (The Pile)

Max Activating Token Index: 678

Text #10

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4770. Min Act: -0.0000

Data Index: 909290 (The Pile)

Max Activating Token Index: 350

Text #11

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4922. Min Act: -0.0000

Data Index: 1838050 (The Pile)

Max Activating Token Index: 882

Text #12

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4863. Min Act: -0.0000

Data Index: 1532945 (The Pile)

Max Activating Token Index: 678

Text #13

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4793. Min Act: -0.0000

Data Index: 1324494 (The Pile)

Max Activating Token Index: 388

Text #14

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1636589 (The Pile)

Max Activating Token Index: 637

Text #15

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4795. Min Act: -0.0000

Data Index: 1659184 (The Pile)

Max Activating Token Index: 41

Text #16

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1604786 (The Pile)

Max Activating Token Index: 244

Text #17

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4770. Min Act: -0.0000

Data Index: 210091 (The Pile)

Max Activating Token Index: 841

Text #18

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4319. Min Act: -0.0000

Data Index: 757370 (The Pile)

Max Activating Token Index: 227

Text #19

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1491290 (The Pile)

Max Activating Token Index: 653