Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 49 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0671. Min Act: -0.0006

Data Index: 1135217 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0660. Min Act: -0.0006

Data Index: 1125213 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0634. Min Act: -0.0006

Data Index: 1136626 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0604. Min Act: -0.0006

Data Index: 1324818 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0589. Min Act: -0.0006

Data Index: 47568 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0573. Min Act: -0.0006

Data Index: 660034 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0585. Min Act: -0.0006

Data Index: 342040 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0579. Min Act: -0.0006

Data Index: 285737 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0573. Min Act: -0.0006

Data Index: 180818 (C4 (Web Text))

Max Activating Token Index: 561

Text #9

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0550. Min Act: -0.0006

Data Index: 590345 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0562. Min Act: -0.0006

Data Index: 454814 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0583. Min Act: -0.0006

Data Index: 206256 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0556. Min Act: -0.0006

Data Index: 189401 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0544. Min Act: -0.0006

Data Index: 809360 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0553. Min Act: -0.0006

Data Index: 635408 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0558. Min Act: -0.0006

Data Index: 1123650 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0543. Min Act: -0.0006

Data Index: 643593 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0546. Min Act: -0.0006

Data Index: 920531 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0546. Min Act: -0.0006

Data Index: 218949 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0537. Min Act: -0.0006

Data Index: 1165285 (C4 (Web Text))

Max Activating Token Index: 1011