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

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

Neuron 5919 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.4902. Min Act: -0.0001

Data Index: 1118814 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.3943. Min Act: -0.0001

Data Index: 1204908 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.0769. Min Act: -0.0001

Data Index: 1253786 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 3.4902. Min Range: -3.4902

Max Act: 3.2281. Min Act: -0.0001

Data Index: 1319465 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.9064. Min Act: -0.0001

Data Index: 779108 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.8806. Min Act: -0.0001

Data Index: 743640 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.9617. Min Act: -0.0001

Data Index: 1347304 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.9218. Min Act: -0.0001

Data Index: 92941 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.7818. Min Act: -0.0001

Data Index: 562532 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.7016. Min Act: -0.0001

Data Index: 509055 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.9820. Min Act: -0.0001

Data Index: 245252 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.7120. Min Act: -0.0001

Data Index: 1139573 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.8310. Min Act: -0.0001

Data Index: 1069509 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.7720. Min Act: -0.0001

Data Index: 521409 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.9300. Min Act: -0.0001

Data Index: 1075363 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.6811. Min Act: -0.0001

Data Index: 365366 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.8950. Min Act: -0.0001

Data Index: 875626 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.8610. Min Act: -0.0001

Data Index: 1022037 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.7453. Min Act: -0.0001

Data Index: 629010 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 3.4902. Min Range: -3.4902

Max Act: 2.7158. Min Act: -0.0001

Data Index: 206300 (C4 (Web Text))

Max Activating Token Index: 455