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

Dataset: The Pile

Neuron 3662 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: 0.2508. Min Range: -0.2508

Max Act: 0.2473. Min Act: -0.0000

Data Index: 44000 (The Pile)

Max Activating Token Index: 270

Text #1

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2508. Min Act: -0.0000

Data Index: 1246240 (The Pile)

Max Activating Token Index: 739

Text #2

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2231. Min Act: -0.0000

Data Index: 15098 (The Pile)

Max Activating Token Index: 689

Text #3

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1995106 (The Pile)

Max Activating Token Index: 389

Text #4

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2240. Min Act: -0.0000

Data Index: 905648 (The Pile)

Max Activating Token Index: 169

Text #5

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2208. Min Act: -0.0000

Data Index: 1605276 (The Pile)

Max Activating Token Index: 479

Text #6

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2179. Min Act: -0.0000

Data Index: 1278331 (The Pile)

Max Activating Token Index: 377

Text #7

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2228. Min Act: -0.0000

Data Index: 732896 (The Pile)

Max Activating Token Index: 238

Text #8

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2140. Min Act: -0.0000

Data Index: 1174859 (The Pile)

Max Activating Token Index: 788

Text #9

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1098571 (The Pile)

Max Activating Token Index: 497

Text #10

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2332. Min Act: -0.0000

Data Index: 221519 (The Pile)

Max Activating Token Index: 829

Text #11

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2116. Min Act: -0.0000

Data Index: 67953 (The Pile)

Max Activating Token Index: 137

Text #12

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1994. Min Act: -0.0000

Data Index: 438625 (The Pile)

Max Activating Token Index: 461

Text #13

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2000. Min Act: -0.0000

Data Index: 211827 (The Pile)

Max Activating Token Index: 52

Text #14

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2082. Min Act: -0.0000

Data Index: 1404993 (The Pile)

Max Activating Token Index: 678

Text #15

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.1980. Min Act: -0.0000

Data Index: 658032 (The Pile)

Max Activating Token Index: 851

Text #16

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1225489 (The Pile)

Max Activating Token Index: 852

Text #17

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2028. Min Act: -0.0000

Data Index: 777708 (The Pile)

Max Activating Token Index: 621

Text #18

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2184. Min Act: -0.0000

Data Index: 598462 (The Pile)

Max Activating Token Index: 969

Text #19

Max Range: 0.2508. Min Range: -0.2508

Max Act: 0.2002. Min Act: -0.0000

Data Index: 384005 (The Pile)

Max Activating Token Index: 785