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

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

Neuron 1593 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0647. Min Act: -0.0002

Data Index: 62073 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0602. Min Act: -0.0003

Data Index: 762025 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0611. Min Act: -0.0003

Data Index: 596829 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0597. Min Act: -0.0003

Data Index: 552893 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0593. Min Act: -0.0003

Data Index: 265753 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0563. Min Act: -0.0003

Data Index: 1141944 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0611. Min Act: -0.0003

Data Index: 206009 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0602. Min Act: -0.0003

Data Index: 1224655 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0580. Min Act: -0.0003

Data Index: 944510 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0585. Min Act: -0.0004

Data Index: 1315214 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0562. Min Act: -0.0002

Data Index: 779262 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0571. Min Act: -0.0003

Data Index: 238690 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0582. Min Act: -0.0003

Data Index: 294554 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0564. Min Act: -0.0003

Data Index: 1311739 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0557. Min Act: -0.0003

Data Index: 103334 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0559. Min Act: -0.0003

Data Index: 998023 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0539. Min Act: -0.0004

Data Index: 559041 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0542. Min Act: -0.0003

Data Index: 993495 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0546. Min Act: -0.0003

Data Index: 818164 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.0647. Min Range: -0.0647

Max Act: 0.0557. Min Act: -0.0003

Data Index: 62031 (C4 (Web Text))

Max Activating Token Index: 378