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

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

Neuron 4018 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: 0.6463. Min Range: -0.6463

Max Act: 0.6463. Min Act: -0.0001

Data Index: 698663 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.6463. Min Range: -0.6463

Max Act: 0.5182. Min Act: -0.0001

Data Index: 669210 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 0.6463. Min Range: -0.6463

Max Act: 0.5713. Min Act: -0.0001

Data Index: 50340 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.6463. Min Range: -0.6463

Max Act: 0.5478. Min Act: -0.0001

Data Index: 1052811 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.6463. Min Range: -0.6463

Max Act: 0.5351. Min Act: -0.0001

Data Index: 635681 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.6463. Min Range: -0.6463

Max Act: 0.5174. Min Act: -0.0001

Data Index: 1185000 (C4 (Web Text))

Max Activating Token Index: 551

Text #6

Max Range: 0.6463. Min Range: -0.6463

Max Act: 0.4825. Min Act: -0.0001

Data Index: 600629 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.6463. Min Range: -0.6463

Max Act: 0.5376. Min Act: -0.0001

Data Index: 427687 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 0.6463. Min Range: -0.6463

Max Act: 0.4972. Min Act: -0.0001

Data Index: 458614 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.6463. Min Range: -0.6463

Max Act: 0.5155. Min Act: -0.0001

Data Index: 210892 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 0.6463. Min Range: -0.6463

Max Act: 0.5125. Min Act: -0.0001

Data Index: 600509 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.6463. Min Range: -0.6463

Max Act: 0.5114. Min Act: -0.0001

Data Index: 507572 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.6463. Min Range: -0.6463

Max Act: 0.5276. Min Act: -0.0001

Data Index: 218749 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.6463. Min Range: -0.6463

Max Act: 0.5061. Min Act: -0.0001

Data Index: 1346101 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.6463. Min Range: -0.6463

Max Act: 0.5076. Min Act: -0.0001

Data Index: 305315 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 0.6463. Min Range: -0.6463

Max Act: 0.5136. Min Act: -0.0001

Data Index: 1123286 (C4 (Web Text))

Max Activating Token Index: 74

Text #16

Max Range: 0.6463. Min Range: -0.6463

Max Act: 0.4900. Min Act: -0.0001

Data Index: 85269 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.6463. Min Range: -0.6463

Max Act: 0.4827. Min Act: -0.0001

Data Index: 844645 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 0.6463. Min Range: -0.6463

Max Act: 0.5040. Min Act: -0.0001

Data Index: 655 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 0.6463. Min Range: -0.6463

Max Act: 0.5020. Min Act: -0.0001

Data Index: 189847 (C4 (Web Text))

Max Activating Token Index: 625