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

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

Neuron 5620 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0742. Min Act: -0.0001

Data Index: 498565 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0718. Min Act: -0.0001

Data Index: 462460 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0642. Min Act: -0.0001

Data Index: 684034 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1261673 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0584. Min Act: -0.0001

Data Index: 633785 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0571. Min Act: -0.0001

Data Index: 212955 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0529. Min Act: -0.0001

Data Index: 998501 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0517. Min Act: -0.0001

Data Index: 822966 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0621. Min Act: -0.0001

Data Index: 819294 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0621. Min Act: -0.0001

Data Index: 138624 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0532. Min Act: -0.0001

Data Index: 46897 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0574. Min Act: -0.0001

Data Index: 284295 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0540. Min Act: -0.0001

Data Index: 727610 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0545. Min Act: -0.0002

Data Index: 947154 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0544. Min Act: -0.0001

Data Index: 983976 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0481. Min Act: -0.0001

Data Index: 1010932 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0520. Min Act: -0.0001

Data Index: 1262283 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0623. Min Act: -0.0001

Data Index: 221683 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0619. Min Act: -0.0001

Data Index: 605724 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0566. Min Act: -0.0001

Data Index: 1296757 (C4 (Web Text))

Max Activating Token Index: 136