Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5101 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.6480. Min Act: -0.0000

Data Index: 29507 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.6614. Min Act: 0.0001

Data Index: 1186351 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.6800. Min Act: 0.0000

Data Index: 850317 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1103535 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.6674. Min Act: -0.0000

Data Index: 563921 (C4 (Web Text))

Max Activating Token Index: 278

Text #5

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.5905. Min Act: -0.0000

Data Index: 582322 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.6232. Min Act: -0.0000

Data Index: 1133214 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1222989 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.5096. Min Act: -0.0000

Data Index: 9961 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.4668. Min Act: -0.0000

Data Index: 1050905 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.5056. Min Act: 0.0000

Data Index: 1164177 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.5049. Min Act: -0.0000

Data Index: 1186583 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.4474. Min Act: -0.0000

Data Index: 159853 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.4698. Min Act: -0.0000

Data Index: 1349837 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.4697. Min Act: 0.0001

Data Index: 167197 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.4521. Min Act: 0.0000

Data Index: 1005999 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.4411. Min Act: 0.0001

Data Index: 564501 (C4 (Web Text))

Max Activating Token Index: 683

Text #17

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.4403. Min Act: -0.0000

Data Index: 1025691 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.4239. Min Act: -0.0000

Data Index: 823926 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 0.6800. Min Range: -0.6800

Max Act: 0.4374. Min Act: 0.0000

Data Index: 168941 (C4 (Web Text))

Max Activating Token Index: 614