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

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

Neuron 3246 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.3494. Min Act: -0.0001

Data Index: 161843 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.3335. Min Act: -0.0001

Data Index: 1145590 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.3229. Min Act: -0.0001

Data Index: 1337401 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.3258. Min Act: -0.0000

Data Index: 493765 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.3092. Min Act: -0.0000

Data Index: 530836 (C4 (Web Text))

Max Activating Token Index: 923

Text #5

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.3277. Min Act: -0.0000

Data Index: 612856 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.3041. Min Act: -0.0001

Data Index: 808211 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2896. Min Act: -0.0001

Data Index: 441715 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.3009. Min Act: -0.0000

Data Index: 758378 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2831. Min Act: -0.0001

Data Index: 674886 (C4 (Web Text))

Max Activating Token Index: 518

Text #10

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2759. Min Act: -0.0001

Data Index: 1192449 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2909. Min Act: -0.0001

Data Index: 899887 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2694. Min Act: -0.0001

Data Index: 492872 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2783. Min Act: -0.0001

Data Index: 987882 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2627. Min Act: -0.0000

Data Index: 520509 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2535. Min Act: -0.0001

Data Index: 591734 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2616. Min Act: -0.0001

Data Index: 597301 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2527. Min Act: -0.0001

Data Index: 541660 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2580. Min Act: -0.0000

Data Index: 637399 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.3494. Min Range: -0.3494

Max Act: 0.2557. Min Act: -0.0001

Data Index: 1313331 (C4 (Web Text))

Max Activating Token Index: 639