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

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

Neuron 3982 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0709. Min Act: -0.0001

Data Index: 501232 (C4 (Web Text))

Max Activating Token Index: 527

Text #1

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0623. Min Act: -0.0000

Data Index: 255344 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0745. Min Act: -0.0000

Data Index: 449041 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0595. Min Act: -0.0000

Data Index: 876393 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0485. Min Act: -0.0000

Data Index: 352599 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0445. Min Act: -0.0000

Data Index: 145890 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0433. Min Act: -0.0000

Data Index: 1352952 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0573. Min Act: -0.0000

Data Index: 1018422 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0480. Min Act: -0.0000

Data Index: 1209664 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0495. Min Act: -0.0000

Data Index: 1317824 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0458. Min Act: -0.0001

Data Index: 430617 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0517. Min Act: -0.0001

Data Index: 638281 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0521. Min Act: -0.0000

Data Index: 864801 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0435. Min Act: -0.0000

Data Index: 1080037 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0487. Min Act: -0.0000

Data Index: 346669 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0479. Min Act: -0.0000

Data Index: 1272607 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0448. Min Act: -0.0000

Data Index: 791178 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0382. Min Act: -0.0000

Data Index: 407087 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0392. Min Act: -0.0000

Data Index: 121153 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 0.0745. Min Range: -0.0745

Max Act: 0.0428. Min Act: -0.0001

Data Index: 686540 (C4 (Web Text))

Max Activating Token Index: 198