Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1848 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0748. Min Act: -0.0006

Data Index: 830332 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0649. Min Act: -0.0006

Data Index: 957535 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0639. Min Act: -0.0006

Data Index: 733259 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0639. Min Act: -0.0006

Data Index: 670294 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0632. Min Act: -0.0006

Data Index: 1125414 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0619. Min Act: -0.0006

Data Index: 720093 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0599. Min Act: -0.0006

Data Index: 1295694 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0587. Min Act: -0.0006

Data Index: 269640 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0612. Min Act: -0.0006

Data Index: 896142 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0594. Min Act: -0.0006

Data Index: 225589 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0603. Min Act: -0.0006

Data Index: 12811 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0602. Min Act: -0.0006

Data Index: 1249484 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0564. Min Act: -0.0006

Data Index: 144829 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0551. Min Act: -0.0006

Data Index: 1143148 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0556. Min Act: -0.0006

Data Index: 438814 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0554. Min Act: -0.0006

Data Index: 586762 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0554. Min Act: -0.0006

Data Index: 997443 (C4 (Web Text))

Max Activating Token Index: 84

Text #17

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0550. Min Act: -0.0005

Data Index: 683689 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0550. Min Act: -0.0006

Data Index: 658489 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.0748. Min Range: -0.0748

Max Act: 0.0560. Min Act: -0.0006

Data Index: 308712 (C4 (Web Text))

Max Activating Token Index: 874