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

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

Neuron 3999 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.4890. Min Act: -0.0000

Data Index: 405824 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.4928. Min Act: -0.0000

Data Index: 453674 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.4155. Min Act: -0.0000

Data Index: 462149 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.4275. Min Act: -0.0000

Data Index: 660574 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.4671. Min Act: -0.0000

Data Index: 885014 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.4138. Min Act: -0.0000

Data Index: 468510 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3978. Min Act: -0.0000

Data Index: 164916 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.4045. Min Act: -0.0000

Data Index: 227841 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.4206. Min Act: -0.0000

Data Index: 193084 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3875. Min Act: -0.0000

Data Index: 290268 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3732. Min Act: -0.0000

Data Index: 201179 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.4091. Min Act: -0.0000

Data Index: 733179 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.4053. Min Act: -0.0000

Data Index: 79381 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3735. Min Act: -0.0000

Data Index: 988046 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3649. Min Act: -0.0000

Data Index: 392302 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3838. Min Act: -0.0000

Data Index: 224098 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3431. Min Act: -0.0000

Data Index: 259368 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3687. Min Act: -0.0000

Data Index: 464034 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3412. Min Act: -0.0000

Data Index: 1111924 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.4928. Min Range: -0.4928

Max Act: 0.3651. Min Act: -0.0000

Data Index: 1129160 (C4 (Web Text))

Max Activating Token Index: 199