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

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

Neuron 4513 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4772. Min Range: -2.4772

Max Act: 2.4568. Min Act: -0.0000

Data Index: 184947 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 2.4772. Min Range: -2.4772

Max Act: 2.4772. Min Act: -0.0000

Data Index: 482831 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 2.4772. Min Range: -2.4772

Max Act: 1.9176. Min Act: -0.0000

Data Index: 1317975 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 2.4772. Min Range: -2.4772

Max Act: 2.2401. Min Act: -0.0000

Data Index: 102679 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 2.4772. Min Range: -2.4772

Max Act: 2.1077. Min Act: -0.0000

Data Index: 661670 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 2.4772. Min Range: -2.4772

Max Act: 2.0327. Min Act: -0.0000

Data Index: 1092698 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 2.4772. Min Range: -2.4772

Max Act: 2.0730. Min Act: -0.0000

Data Index: 1241817 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 2.4772. Min Range: -2.4772

Max Act: 2.0482. Min Act: -0.0000

Data Index: 114129 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 2.4772. Min Range: -2.4772

Max Act: 2.0715. Min Act: -0.0000

Data Index: 1048350 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 2.4772. Min Range: -2.4772

Max Act: 2.0218. Min Act: -0.0000

Data Index: 1000751 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 2.4772. Min Range: -2.4772

Max Act: 1.7976. Min Act: -0.0000

Data Index: 398448 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 2.4772. Min Range: -2.4772

Max Act: 1.9358. Min Act: -0.0000

Data Index: 837564 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 2.4772. Min Range: -2.4772

Max Act: 1.8808. Min Act: -0.0000

Data Index: 70453 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 2.4772. Min Range: -2.4772

Max Act: 1.9648. Min Act: -0.0000

Data Index: 1017237 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 2.4772. Min Range: -2.4772

Max Act: 1.9071. Min Act: -0.0000

Data Index: 415680 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 2.4772. Min Range: -2.4772

Max Act: 1.7939. Min Act: -0.0000

Data Index: 1003689 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 2.4772. Min Range: -2.4772

Max Act: 1.8379. Min Act: -0.0000

Data Index: 607381 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 2.4772. Min Range: -2.4772

Max Act: 1.8227. Min Act: -0.0000

Data Index: 816311 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 2.4772. Min Range: -2.4772

Max Act: 1.7427. Min Act: -0.0000

Data Index: 299472 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 2.4772. Min Range: -2.4772

Max Act: 1.6359. Min Act: -0.0000

Data Index: 352046 (C4 (Web Text))

Max Activating Token Index: 300