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

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

Neuron 2717 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1293. Min Range: -1.1293

Max Act: 1.0317. Min Act: -0.0001

Data Index: 1348126 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 1.1293. Min Range: -1.1293

Max Act: 1.1293. Min Act: -0.0001

Data Index: 479951 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.9095. Min Act: -0.0001

Data Index: 114825 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.9435. Min Act: -0.0001

Data Index: 856154 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.9784. Min Act: -0.0001

Data Index: 562133 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.9942. Min Act: -0.0001

Data Index: 899230 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.9690. Min Act: -0.0001

Data Index: 348474 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.9792. Min Act: -0.0001

Data Index: 997579 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.7889. Min Act: -0.0001

Data Index: 973220 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.9644. Min Act: -0.0001

Data Index: 287523 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.9718. Min Act: -0.0001

Data Index: 554945 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.8431. Min Act: -0.0001

Data Index: 868670 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.8481. Min Act: -0.0001

Data Index: 320587 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.8860. Min Act: -0.0001

Data Index: 1291867 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.8958. Min Act: -0.0001

Data Index: 994009 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.8713. Min Act: -0.0001

Data Index: 1319466 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.8249. Min Act: -0.0001

Data Index: 1289168 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.8647. Min Act: -0.0001

Data Index: 686178 (C4 (Web Text))

Max Activating Token Index: 823

Text #18

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.8438. Min Act: -0.0001

Data Index: 1291723 (C4 (Web Text))

Max Activating Token Index: 539

Text #19

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.9649. Min Act: -0.0001

Data Index: 750369 (C4 (Web Text))

Max Activating Token Index: 526