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

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

Neuron 4338 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0743. Min Act: -0.0002

Data Index: 792696 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0706. Min Act: -0.0002

Data Index: 999441 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0633. Min Act: -0.0002

Data Index: 876419 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0642. Min Act: -0.0002

Data Index: 1212614 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0586. Min Act: -0.0002

Data Index: 328736 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0554. Min Act: -0.0002

Data Index: 1494233 (Python Code)

Max Activating Token Index: 262

Text #6

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0571. Min Act: -0.0002

Data Index: 837850 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0549. Min Act: -0.0002

Data Index: 160094 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0547. Min Act: -0.0002

Data Index: 805810 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0539. Min Act: -0.0002

Data Index: 364347 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0526. Min Act: -0.0002

Data Index: 286777 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0553. Min Act: -0.0002

Data Index: 272073 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0500. Min Act: -0.0002

Data Index: 641357 (C4 (Web Text))

Max Activating Token Index: 933

Text #13

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0549. Min Act: -0.0002

Data Index: 10455 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1149250 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0495. Min Act: -0.0002

Data Index: 1155230 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1050251 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0520. Min Act: -0.0002

Data Index: 1234678 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0494. Min Act: -0.0002

Data Index: 871329 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0510. Min Act: -0.0002

Data Index: 425603 (C4 (Web Text))

Max Activating Token Index: 241