Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 161 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0751. Min Act: -0.0004

Data Index: 173332 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0676. Min Act: -0.0004

Data Index: 188151 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0611. Min Act: -0.0003

Data Index: 334970 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0605. Min Act: -0.0003

Data Index: 96388 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0597. Min Act: -0.0003

Data Index: 825764 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0554. Min Act: -0.0003

Data Index: 222222 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0548. Min Act: -0.0003

Data Index: 904642 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0531. Min Act: -0.0003

Data Index: 32880 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0508. Min Act: -0.0004

Data Index: 158945 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0566. Min Act: -0.0003

Data Index: 316956 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0516. Min Act: -0.0003

Data Index: 675345 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0556. Min Act: -0.0004

Data Index: 528941 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0555. Min Act: -0.0003

Data Index: 776836 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0553. Min Act: -0.0003

Data Index: 1045885 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0539. Min Act: -0.0003

Data Index: 682388 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0545. Min Act: -0.0003

Data Index: 1072549 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0533. Min Act: -0.0003

Data Index: 850463 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0533. Min Act: -0.0003

Data Index: 296336 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0558. Min Act: -0.0004

Data Index: 457605 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0548. Min Act: -0.0003

Data Index: 1208980 (C4 (Web Text))

Max Activating Token Index: 383