Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1170 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1001245 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0680. Min Act: -0.0002

Data Index: 949939 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0643. Min Act: -0.0002

Data Index: 475554 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0625. Min Act: -0.0002

Data Index: 548991 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0602. Min Act: -0.0002

Data Index: 477622 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0619. Min Act: -0.0002

Data Index: 545366 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0603. Min Act: -0.0002

Data Index: 225706 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1332618 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0584. Min Act: -0.0002

Data Index: 235413 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1091198 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1286164 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0594. Min Act: -0.0002

Data Index: 173317 (C4 (Web Text))

Max Activating Token Index: 846

Text #12

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0542. Min Act: -0.0002

Data Index: 687298 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0540. Min Act: -0.0002

Data Index: 748260 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0552. Min Act: -0.0002

Data Index: 891286 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1032257 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0554. Min Act: -0.0002

Data Index: 12462 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1332378 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0555. Min Act: -0.0002

Data Index: 27717 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 0.0680. Min Range: -0.0680

Max Act: 0.0574. Min Act: -0.0002

Data Index: 144916 (C4 (Web Text))

Max Activating Token Index: 931