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

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

Neuron 1141 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9416. Min Range: -2.9416

Max Act: 2.7843. Min Act: -0.0000

Data Index: 8297 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 2.9416. Min Range: -2.9416

Max Act: 2.9416. Min Act: -0.0000

Data Index: 1242736 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 2.9416. Min Range: -2.9416

Max Act: 2.4655. Min Act: -0.0000

Data Index: 701933 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 2.9416. Min Range: -2.9416

Max Act: 2.7582. Min Act: -0.0000

Data Index: 116497 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 2.9416. Min Range: -2.9416

Max Act: 2.6520. Min Act: -0.0000

Data Index: 137708 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 2.9416. Min Range: -2.9416

Max Act: 2.7366. Min Act: -0.0000

Data Index: 679789 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 2.9416. Min Range: -2.9416

Max Act: 2.1731. Min Act: -0.0000

Data Index: 5618 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 2.9416. Min Range: -2.9416

Max Act: 1.9907. Min Act: -0.0000

Data Index: 658663 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 2.9416. Min Range: -2.9416

Max Act: 1.7730. Min Act: -0.0000

Data Index: 786895 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 2.9416. Min Range: -2.9416

Max Act: 2.0784. Min Act: -0.0000

Data Index: 1225296 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 2.9416. Min Range: -2.9416

Max Act: 1.8376. Min Act: -0.0000

Data Index: 481553 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 2.9416. Min Range: -2.9416

Max Act: 1.8868. Min Act: -0.0000

Data Index: 397655 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 2.9416. Min Range: -2.9416

Max Act: 1.7542. Min Act: -0.0000

Data Index: 794825 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 2.9416. Min Range: -2.9416

Max Act: 1.8572. Min Act: -0.0000

Data Index: 809875 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 2.9416. Min Range: -2.9416

Max Act: 1.7509. Min Act: -0.0000

Data Index: 30962 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 2.9416. Min Range: -2.9416

Max Act: 1.7012. Min Act: -0.0000

Data Index: 389632 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 2.9416. Min Range: -2.9416

Max Act: 1.6086. Min Act: -0.0000

Data Index: 793307 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 2.9416. Min Range: -2.9416

Max Act: 1.6621. Min Act: -0.0000

Data Index: 216485 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 2.9416. Min Range: -2.9416

Max Act: 1.4886. Min Act: -0.0000

Data Index: 392531 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 2.9416. Min Range: -2.9416

Max Act: 1.5600. Min Act: -0.0000

Data Index: 486214 (C4 (Web Text))

Max Activating Token Index: 729