Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3520 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0934. Min Act: -0.0001

Data Index: 999822 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0901. Min Act: -0.0001

Data Index: 949026 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0854. Min Act: -0.0002

Data Index: 851579 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0786. Min Act: -0.0001

Data Index: 1023812 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0745. Min Act: -0.0002

Data Index: 825050 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0667. Min Act: -0.0002

Data Index: 468383 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0725. Min Act: -0.0001

Data Index: 135765 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0657. Min Act: -0.0001

Data Index: 775539 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1113786 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0617. Min Act: -0.0001

Data Index: 519063 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0605. Min Act: -0.0001

Data Index: 437698 (C4 (Web Text))

Max Activating Token Index: 904

Text #11

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0593. Min Act: -0.0001

Data Index: 554073 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0574. Min Act: -0.0001

Data Index: 1239346 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0670. Min Act: -0.0002

Data Index: 763105 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0593. Min Act: -0.0001

Data Index: 736012 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0615. Min Act: -0.0001

Data Index: 1205010 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0565. Min Act: -0.0002

Data Index: 278329 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0588. Min Act: -0.0001

Data Index: 1099261 (C4 (Web Text))

Max Activating Token Index: 505

Text #18

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0607. Min Act: -0.0001

Data Index: 770883 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0582. Min Act: -0.0001

Data Index: 1349429 (C4 (Web Text))

Max Activating Token Index: 483