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

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

Neuron 4371 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: 4.4168. Min Range: -4.4168

Max Act: 4.4168. Min Act: -0.0000

Data Index: 1146673 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 4.4168. Min Range: -4.4168

Max Act: 2.9746. Min Act: -0.0000

Data Index: 283916 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 4.4168. Min Range: -4.4168

Max Act: 2.9119. Min Act: -0.0000

Data Index: 260648 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 4.4168. Min Range: -4.4168

Max Act: 3.0614. Min Act: -0.0000

Data Index: 837306 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 4.4168. Min Range: -4.4168

Max Act: 2.9088. Min Act: -0.0000

Data Index: 749226 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 4.4168. Min Range: -4.4168

Max Act: 2.8898. Min Act: -0.0000

Data Index: 491320 (C4 (Web Text))

Max Activating Token Index: 702

Text #6

Max Range: 4.4168. Min Range: -4.4168

Max Act: 2.8640. Min Act: -0.0000

Data Index: 27048 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 4.4168. Min Range: -4.4168

Max Act: 2.7549. Min Act: -0.0000

Data Index: 1351492 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 4.4168. Min Range: -4.4168

Max Act: 2.7437. Min Act: -0.0000

Data Index: 757365 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 4.4168. Min Range: -4.4168

Max Act: 2.9860. Min Act: -0.0000

Data Index: 1077804 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 4.4168. Min Range: -4.4168

Max Act: 2.9804. Min Act: -0.0000

Data Index: 747907 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 4.4168. Min Range: -4.4168

Max Act: 3.2271. Min Act: -0.0000

Data Index: 905918 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 4.4168. Min Range: -4.4168

Max Act: 2.6406. Min Act: -0.0000

Data Index: 1171918 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 4.4168. Min Range: -4.4168

Max Act: 3.0659. Min Act: -0.0000

Data Index: 538622 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 4.4168. Min Range: -4.4168

Max Act: 2.8922. Min Act: -0.0000

Data Index: 1319241 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 4.4168. Min Range: -4.4168

Max Act: 2.6013. Min Act: -0.0000

Data Index: 54000 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 4.4168. Min Range: -4.4168

Max Act: 2.5891. Min Act: -0.0000

Data Index: 1037049 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 4.4168. Min Range: -4.4168

Max Act: 2.6707. Min Act: -0.0000

Data Index: 314344 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 4.4168. Min Range: -4.4168

Max Act: 2.5331. Min Act: -0.0000

Data Index: 551787 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 4.4168. Min Range: -4.4168

Max Act: 2.6582. Min Act: -0.0000

Data Index: 574961 (C4 (Web Text))

Max Activating Token Index: 725