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

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

Neuron 5233 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1086636 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.4411. Min Act: -0.0000

Data Index: 1215884 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.4125. Min Act: -0.0000

Data Index: 1046229 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3996. Min Act: -0.0000

Data Index: 7015 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.4348. Min Act: -0.0000

Data Index: 380611 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.4122. Min Act: -0.0000

Data Index: 161962 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3953. Min Act: -0.0000

Data Index: 1096978 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3628. Min Act: -0.0000

Data Index: 119041 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3772. Min Act: -0.0000

Data Index: 1003108 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3341. Min Act: -0.0000

Data Index: 22417 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3669. Min Act: -0.0000

Data Index: 979313 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3395. Min Act: -0.0000

Data Index: 1160987 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3638. Min Act: -0.0000

Data Index: 656445 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3590. Min Act: -0.0000

Data Index: 216467 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3432. Min Act: -0.0000

Data Index: 832370 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3237. Min Act: -0.0000

Data Index: 952195 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3685. Min Act: -0.0000

Data Index: 341469 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3274. Min Act: -0.0000

Data Index: 1083172 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3739. Min Act: -0.0000

Data Index: 831511 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 0.4840. Min Range: -0.4840

Max Act: 0.3349. Min Act: -0.0000

Data Index: 266964 (C4 (Web Text))

Max Activating Token Index: 59