Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3062 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0686. Min Act: -0.0003

Data Index: 840506 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0637. Min Act: -0.0003

Data Index: 483050 (C4 (Web Text))

Max Activating Token Index: 194

Text #2

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1461302 (Python Code)

Max Activating Token Index: 664

Text #3

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1597539 (Python Code)

Max Activating Token Index: 310

Text #4

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0555. Min Act: -0.0003

Data Index: 74065 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0585. Min Act: -0.0003

Data Index: 1437096 (Python Code)

Max Activating Token Index: 683

Text #6

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0567. Min Act: -0.0003

Data Index: 1089990 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0559. Min Act: -0.0003

Data Index: 373014 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0548. Min Act: -0.0003

Data Index: 1015085 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0556. Min Act: -0.0003

Data Index: 795970 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1491752 (Python Code)

Max Activating Token Index: 479

Text #11

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1542534 (Python Code)

Max Activating Token Index: 468

Text #12

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0558. Min Act: -0.0003

Data Index: 1168958 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0545. Min Act: -0.0003

Data Index: 1358849 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0557. Min Act: -0.0003

Data Index: 694109 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0550. Min Act: -0.0003

Data Index: 429191 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0553. Min Act: -0.0003

Data Index: 288693 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0530. Min Act: -0.0003

Data Index: 38007 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0518. Min Act: -0.0003

Data Index: 1415269 (Python Code)

Max Activating Token Index: 509

Text #19

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0515. Min Act: -0.0003

Data Index: 1587273 (Python Code)

Max Activating Token Index: 317