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

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

Neuron 3428 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: 3.6499. Min Range: -3.6499

Max Act: 3.6499. Min Act: -0.0000

Data Index: 373016 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 3.6499. Min Range: -3.6499

Max Act: 3.0398. Min Act: -0.0000

Data Index: 656214 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 3.6499. Min Range: -3.6499

Max Act: 3.1092. Min Act: -0.0000

Data Index: 45113 (C4 (Web Text))

Max Activating Token Index: 793

Text #3

Max Range: 3.6499. Min Range: -3.6499

Max Act: 3.1041. Min Act: -0.0000

Data Index: 707976 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 3.6499. Min Range: -3.6499

Max Act: 2.8016. Min Act: -0.0000

Data Index: 712003 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 3.6499. Min Range: -3.6499

Max Act: 2.5897. Min Act: -0.0000

Data Index: 655344 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 3.6499. Min Range: -3.6499

Max Act: 3.1085. Min Act: -0.0000

Data Index: 1130866 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 3.6499. Min Range: -3.6499

Max Act: 2.9457. Min Act: -0.0000

Data Index: 161015 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 3.6499. Min Range: -3.6499

Max Act: 2.6394. Min Act: -0.0000

Data Index: 1300707 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 3.6499. Min Range: -3.6499

Max Act: 2.8550. Min Act: -0.0000

Data Index: 458723 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 3.6499. Min Range: -3.6499

Max Act: 2.7179. Min Act: -0.0000

Data Index: 54453 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 3.6499. Min Range: -3.6499

Max Act: 2.5127. Min Act: -0.0000

Data Index: 1091985 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 3.6499. Min Range: -3.6499

Max Act: 2.7313. Min Act: -0.0000

Data Index: 264797 (C4 (Web Text))

Max Activating Token Index: 406

Text #13

Max Range: 3.6499. Min Range: -3.6499

Max Act: 2.4047. Min Act: -0.0000

Data Index: 812182 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 3.6499. Min Range: -3.6499

Max Act: 2.5928. Min Act: -0.0000

Data Index: 842177 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 3.6499. Min Range: -3.6499

Max Act: 2.5575. Min Act: -0.0000

Data Index: 327863 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 3.6499. Min Range: -3.6499

Max Act: 2.5666. Min Act: -0.0000

Data Index: 1760 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 3.6499. Min Range: -3.6499

Max Act: 2.4352. Min Act: -0.0000

Data Index: 206762 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 3.6499. Min Range: -3.6499

Max Act: 2.2904. Min Act: -0.0000

Data Index: 691175 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 3.6499. Min Range: -3.6499

Max Act: 2.3799. Min Act: -0.0000

Data Index: 74318 (C4 (Web Text))

Max Activating Token Index: 568