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

Dataset: The Pile

Neuron 3920 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: 0.7618. Min Range: -0.7618

Max Act: 0.7618. Min Act: -0.0000

Data Index: 685463 (The Pile)

Max Activating Token Index: 479

Text #1

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.7597. Min Act: -0.0000

Data Index: 519092 (The Pile)

Max Activating Token Index: 988

Text #2

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.7532. Min Act: -0.0000

Data Index: 1410891 (The Pile)

Max Activating Token Index: 992

Text #3

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.7092. Min Act: -0.0000

Data Index: 832906 (The Pile)

Max Activating Token Index: 697

Text #4

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6096. Min Act: -0.0000

Data Index: 1326647 (The Pile)

Max Activating Token Index: 65

Text #5

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6888. Min Act: -0.0000

Data Index: 12830 (The Pile)

Max Activating Token Index: 152

Text #6

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6323. Min Act: -0.0000

Data Index: 736545 (The Pile)

Max Activating Token Index: 445

Text #7

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6474. Min Act: -0.0000

Data Index: 1755235 (The Pile)

Max Activating Token Index: 419

Text #8

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.7028. Min Act: -0.0000

Data Index: 998071 (The Pile)

Max Activating Token Index: 625

Text #9

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1403812 (The Pile)

Max Activating Token Index: 528

Text #10

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6454. Min Act: -0.0000

Data Index: 159895 (The Pile)

Max Activating Token Index: 218

Text #11

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6292. Min Act: -0.0000

Data Index: 326090 (The Pile)

Max Activating Token Index: 1021

Text #12

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.5607. Min Act: -0.0001

Data Index: 1260301 (The Pile)

Max Activating Token Index: 989

Text #13

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.5167. Min Act: -0.0001

Data Index: 343091 (The Pile)

Max Activating Token Index: 795

Text #14

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.5699. Min Act: -0.0000

Data Index: 484466 (The Pile)

Max Activating Token Index: 908

Text #15

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.5641. Min Act: -0.0000

Data Index: 64568 (The Pile)

Max Activating Token Index: 563

Text #16

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6056. Min Act: -0.0000

Data Index: 1744144 (The Pile)

Max Activating Token Index: 105

Text #17

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.5950. Min Act: -0.0000

Data Index: 1858834 (The Pile)

Max Activating Token Index: 487

Text #18

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.5967. Min Act: -0.0000

Data Index: 327948 (The Pile)

Max Activating Token Index: 185

Text #19

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6008. Min Act: -0.0000

Data Index: 571765 (The Pile)

Max Activating Token Index: 552