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

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

Neuron 5743 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0799. Min Act: -0.0000

Data Index: 602731 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0619. Min Act: -0.0000

Data Index: 356159 (C4 (Web Text))

Max Activating Token Index: 485

Text #2

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0557. Min Act: -0.0001

Data Index: 495755 (C4 (Web Text))

Max Activating Token Index: 175

Text #3

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0595. Min Act: -0.0000

Data Index: 270713 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0584. Min Act: -0.0000

Data Index: 708004 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0574. Min Act: -0.0001

Data Index: 1052244 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0595. Min Act: -0.0000

Data Index: 111076 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0497. Min Act: -0.0000

Data Index: 1338436 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0518. Min Act: -0.0000

Data Index: 234656 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0575. Min Act: -0.0000

Data Index: 826785 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0513. Min Act: -0.0000

Data Index: 164496 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0539. Min Act: -0.0000

Data Index: 431842 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0502. Min Act: -0.0000

Data Index: 895429 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0538. Min Act: -0.0000

Data Index: 1017656 (C4 (Web Text))

Max Activating Token Index: 330

Text #14

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0516. Min Act: -0.0000

Data Index: 803458 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0496. Min Act: -0.0000

Data Index: 314578 (C4 (Web Text))

Max Activating Token Index: 471

Text #16

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0465. Min Act: -0.0001

Data Index: 300628 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0472. Min Act: -0.0000

Data Index: 586111 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0521. Min Act: -0.0000

Data Index: 817610 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.0799. Min Range: -0.0799

Max Act: 0.0499. Min Act: -0.0000

Data Index: 519748 (C4 (Web Text))

Max Activating Token Index: 987