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

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

Neuron 443 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0659. Min Act: -0.0002

Data Index: 480145 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1085367 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0626. Min Act: -0.0002

Data Index: 520355 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1123370 (C4 (Web Text))

Max Activating Token Index: 206

Text #4

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0564. Min Act: -0.0002

Data Index: 1245490 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0547. Min Act: -0.0002

Data Index: 922527 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0551. Min Act: -0.0002

Data Index: 213480 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1289691 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1077237 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0539. Min Act: -0.0002

Data Index: 676291 (C4 (Web Text))

Max Activating Token Index: 177

Text #10

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0532. Min Act: -0.0002

Data Index: 1067613 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0548. Min Act: -0.0002

Data Index: 623356 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0530. Min Act: -0.0002

Data Index: 291495 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0543. Min Act: -0.0002

Data Index: 1115354 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0532. Min Act: -0.0002

Data Index: 660715 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0527. Min Act: -0.0002

Data Index: 55738 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0532. Min Act: -0.0002

Data Index: 507669 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1304752 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0531. Min Act: -0.0002

Data Index: 326538 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 0.0659. Min Range: -0.0659

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1035359 (C4 (Web Text))

Max Activating Token Index: 933