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

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

Neuron 1620 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.0754. Min Range: -6.0754

Max Act: 6.0347. Min Act: -0.0000

Data Index: 95153 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 6.0754. Min Range: -6.0754

Max Act: 6.0111. Min Act: -0.0000

Data Index: 64843 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 6.0754. Min Range: -6.0754

Max Act: 5.9700. Min Act: -0.0000

Data Index: 1032592 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 6.0754. Min Range: -6.0754

Max Act: 5.8771. Min Act: -0.0000

Data Index: 444618 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 6.0754. Min Range: -6.0754

Max Act: 5.9072. Min Act: -0.0000

Data Index: 1050927 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 6.0754. Min Range: -6.0754

Max Act: 5.9027. Min Act: -0.0000

Data Index: 549093 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 6.0754. Min Range: -6.0754

Max Act: 6.0754. Min Act: -0.0000

Data Index: 153381 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 6.0754. Min Range: -6.0754

Max Act: 5.7228. Min Act: -0.0000

Data Index: 1169589 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 6.0754. Min Range: -6.0754

Max Act: 5.7150. Min Act: -0.0000

Data Index: 1226309 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 6.0754. Min Range: -6.0754

Max Act: 5.6867. Min Act: -0.0000

Data Index: 627567 (C4 (Web Text))

Max Activating Token Index: 997

Text #10

Max Range: 6.0754. Min Range: -6.0754

Max Act: 5.6840. Min Act: -0.0000

Data Index: 333337 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 6.0754. Min Range: -6.0754

Max Act: 5.4480. Min Act: -0.0000

Data Index: 96729 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 6.0754. Min Range: -6.0754

Max Act: 5.2675. Min Act: -0.0000

Data Index: 592446 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 6.0754. Min Range: -6.0754

Max Act: 3.8437. Min Act: -0.0000

Data Index: 260824 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 6.0754. Min Range: -6.0754

Max Act: 3.5183. Min Act: -0.0000

Data Index: 47070 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 6.0754. Min Range: -6.0754

Max Act: 3.3905. Min Act: -0.0000

Data Index: 1227138 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 6.0754. Min Range: -6.0754

Max Act: 2.9084. Min Act: -0.0000

Data Index: 720140 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 6.0754. Min Range: -6.0754

Max Act: 2.9543. Min Act: -0.0000

Data Index: 493183 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 6.0754. Min Range: -6.0754

Max Act: 2.7850. Min Act: -0.0000

Data Index: 721798 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 6.0754. Min Range: -6.0754

Max Act: 2.8884. Min Act: -0.0000

Data Index: 170663 (C4 (Web Text))

Max Activating Token Index: 433