Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4466 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1024784 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0582. Min Act: -0.0002

Data Index: 1485527 (Python Code)

Max Activating Token Index: 168

Text #2

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1442496 (Python Code)

Max Activating Token Index: 647

Text #3

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0585. Min Act: -0.0002

Data Index: 1296018 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0611. Min Act: -0.0002

Data Index: 872521 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0545. Min Act: -0.0002

Data Index: 1009926 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0528. Min Act: -0.0002

Data Index: 640513 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1368375 (Python Code)

Max Activating Token Index: 62

Text #8

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0557. Min Act: -0.0002

Data Index: 279367 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0508. Min Act: -0.0002

Data Index: 1002612 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0514. Min Act: -0.0002

Data Index: 808508 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0546. Min Act: -0.0002

Data Index: 293572 (C4 (Web Text))

Max Activating Token Index: 1004

Text #12

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0594. Min Act: -0.0002

Data Index: 1073691 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1363467 (Python Code)

Max Activating Token Index: 891

Text #14

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0557. Min Act: -0.0002

Data Index: 701341 (C4 (Web Text))

Max Activating Token Index: 580

Text #15

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0562. Min Act: -0.0002

Data Index: 214554 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0533. Min Act: -0.0002

Data Index: 230006 (C4 (Web Text))

Max Activating Token Index: 481

Text #17

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0510. Min Act: -0.0002

Data Index: 446755 (C4 (Web Text))

Max Activating Token Index: 681

Text #18

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0510. Min Act: -0.0002

Data Index: 808434 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0509. Min Act: -0.0002

Data Index: 127700 (C4 (Web Text))

Max Activating Token Index: 963