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

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

Neuron 31 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9929. Min Range: -0.9929

Max Act: 0.9929. Min Act: -0.0000

Data Index: 328571 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.9929. Min Range: -0.9929

Max Act: 0.9863. Min Act: -0.0000

Data Index: 374782 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.9929. Min Range: -0.9929

Max Act: 0.9117. Min Act: -0.0000

Data Index: 859898 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 0.9929. Min Range: -0.9929

Max Act: 0.9073. Min Act: -0.0000

Data Index: 355292 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.9929. Min Range: -0.9929

Max Act: 0.8580. Min Act: -0.0000

Data Index: 523949 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 0.9929. Min Range: -0.9929

Max Act: 0.8059. Min Act: -0.0000

Data Index: 173622 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 0.9929. Min Range: -0.9929

Max Act: 0.7932. Min Act: -0.0000

Data Index: 1198698 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.9929. Min Range: -0.9929

Max Act: 0.8025. Min Act: -0.0000

Data Index: 1128780 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.9929. Min Range: -0.9929

Max Act: 0.7669. Min Act: -0.0000

Data Index: 173621 (C4 (Web Text))

Max Activating Token Index: 866

Text #9

Max Range: 0.9929. Min Range: -0.9929

Max Act: 0.7304. Min Act: -0.0000

Data Index: 671717 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.9929. Min Range: -0.9929

Max Act: 0.7411. Min Act: -0.0000

Data Index: 193429 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.9929. Min Range: -0.9929

Max Act: 0.7181. Min Act: -0.0001

Data Index: 973555 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.9929. Min Range: -0.9929

Max Act: 0.7612. Min Act: -0.0000

Data Index: 776729 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 0.9929. Min Range: -0.9929

Max Act: 0.6579. Min Act: -0.0001

Data Index: 191409 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 0.9929. Min Range: -0.9929

Max Act: 0.6520. Min Act: -0.0000

Data Index: 331441 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.9929. Min Range: -0.9929

Max Act: 0.6672. Min Act: -0.0000

Data Index: 632123 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.9929. Min Range: -0.9929

Max Act: 0.6512. Min Act: -0.0001

Data Index: 594372 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.9929. Min Range: -0.9929

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1173879 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 0.9929. Min Range: -0.9929

Max Act: 0.6608. Min Act: -0.0000

Data Index: 624689 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.9929. Min Range: -0.9929

Max Act: 0.6375. Min Act: -0.0000

Data Index: 600929 (C4 (Web Text))

Max Activating Token Index: 872