Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2465 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.5908. Min Act: -0.0001

Data Index: 1192001 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.5904. Min Act: -0.0001

Data Index: 254457 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.5138. Min Act: -0.0001

Data Index: 1207771 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4667. Min Act: -0.0001

Data Index: 947666 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.5117. Min Act: -0.0001

Data Index: 353750 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4609. Min Act: -0.0001

Data Index: 622889 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4304. Min Act: -0.0001

Data Index: 1350070 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4471. Min Act: -0.0001

Data Index: 1080396 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4317. Min Act: -0.0001

Data Index: 974059 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4369. Min Act: -0.0001

Data Index: 663753 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4210. Min Act: -0.0001

Data Index: 165584 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.3911. Min Act: -0.0001

Data Index: 1002928 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4077. Min Act: -0.0001

Data Index: 442001 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4037. Min Act: -0.0001

Data Index: 67731 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.3782. Min Act: -0.0001

Data Index: 933975 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.3702. Min Act: -0.0001

Data Index: 80844 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.4098. Min Act: -0.0001

Data Index: 671171 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.3686. Min Act: -0.0001

Data Index: 328901 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.3919. Min Act: -0.0001

Data Index: 798888 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 0.5908. Min Range: -0.5908

Max Act: 0.3651. Min Act: -0.0001

Data Index: 649934 (C4 (Web Text))

Max Activating Token Index: 751