Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3378 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0783. Min Act: -0.0001

Data Index: 644850 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0733. Min Act: -0.0002

Data Index: 1175498 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0640. Min Act: -0.0001

Data Index: 770995 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0630. Min Act: -0.0001

Data Index: 1000368 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0607. Min Act: -0.0002

Data Index: 681346 (C4 (Web Text))

Max Activating Token Index: 727

Text #5

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0580. Min Act: -0.0002

Data Index: 784745 (C4 (Web Text))

Max Activating Token Index: 402

Text #6

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0571. Min Act: -0.0002

Data Index: 896904 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0572. Min Act: -0.0001

Data Index: 673069 (C4 (Web Text))

Max Activating Token Index: 471

Text #8

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1244326 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0566. Min Act: -0.0001

Data Index: 953633 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0539. Min Act: -0.0002

Data Index: 561348 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0535. Min Act: -0.0002

Data Index: 400420 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0553. Min Act: -0.0002

Data Index: 968493 (C4 (Web Text))

Max Activating Token Index: 476

Text #13

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0518. Min Act: -0.0002

Data Index: 904180 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1326310 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0508. Min Act: -0.0001

Data Index: 933652 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1174135 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0502. Min Act: -0.0002

Data Index: 527476 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0529. Min Act: -0.0001

Data Index: 397574 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0507. Min Act: -0.0001

Data Index: 733257 (C4 (Web Text))

Max Activating Token Index: 379