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

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

Neuron 2320 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0702. Min Act: -0.0002

Data Index: 721122 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0652. Min Act: -0.0002

Data Index: 930606 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0648. Min Act: -0.0002

Data Index: 938349 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0625. Min Act: -0.0002

Data Index: 437592 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0620. Min Act: -0.0002

Data Index: 305616 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0624. Min Act: -0.0002

Data Index: 75724 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1136226 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1124827 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0582. Min Act: -0.0002

Data Index: 1179909 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0588. Min Act: -0.0002

Data Index: 626345 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0583. Min Act: -0.0002

Data Index: 953133 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0576. Min Act: -0.0002

Data Index: 606528 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0562. Min Act: -0.0002

Data Index: 463875 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1009632 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0563. Min Act: -0.0002

Data Index: 854153 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0568. Min Act: -0.0002

Data Index: 941901 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0555. Min Act: -0.0002

Data Index: 400391 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0548. Min Act: -0.0002

Data Index: 376824 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0555. Min Act: -0.0002

Data Index: 734021 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 0.0702. Min Range: -0.0702

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1164262 (C4 (Web Text))

Max Activating Token Index: 606