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

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

Neuron 3039 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9029. Min Range: -3.9029

Max Act: 3.9029. Min Act: -0.0001

Data Index: 183866 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 3.9029. Min Range: -3.9029

Max Act: 3.3632. Min Act: -0.0001

Data Index: 1138359 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 3.9029. Min Range: -3.9029

Max Act: 3.4105. Min Act: -0.0001

Data Index: 1080367 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 3.9029. Min Range: -3.9029

Max Act: 3.0827. Min Act: -0.0001

Data Index: 84234 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 3.9029. Min Range: -3.9029

Max Act: 3.2384. Min Act: -0.0000

Data Index: 35858 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 3.9029. Min Range: -3.9029

Max Act: 2.8720. Min Act: -0.0001

Data Index: 305978 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 3.9029. Min Range: -3.9029

Max Act: 2.8139. Min Act: -0.0001

Data Index: 840731 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 3.9029. Min Range: -3.9029

Max Act: 2.6305. Min Act: -0.0001

Data Index: 749601 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 3.9029. Min Range: -3.9029

Max Act: 2.7298. Min Act: -0.0001

Data Index: 634516 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 3.9029. Min Range: -3.9029

Max Act: 2.7248. Min Act: -0.0001

Data Index: 640669 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 3.9029. Min Range: -3.9029

Max Act: 2.8486. Min Act: -0.0001

Data Index: 770883 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 3.9029. Min Range: -3.9029

Max Act: 2.6790. Min Act: -0.0001

Data Index: 923301 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 3.9029. Min Range: -3.9029

Max Act: 2.6519. Min Act: -0.0001

Data Index: 63649 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 3.9029. Min Range: -3.9029

Max Act: 2.6217. Min Act: -0.0001

Data Index: 763761 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 3.9029. Min Range: -3.9029

Max Act: 2.5525. Min Act: -0.0000

Data Index: 596770 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 3.9029. Min Range: -3.9029

Max Act: 2.5615. Min Act: -0.0001

Data Index: 90392 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 3.9029. Min Range: -3.9029

Max Act: 2.7138. Min Act: -0.0001

Data Index: 378326 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 3.9029. Min Range: -3.9029

Max Act: 2.8064. Min Act: -0.0000

Data Index: 445782 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 3.9029. Min Range: -3.9029

Max Act: 2.5244. Min Act: -0.0001

Data Index: 289341 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 3.9029. Min Range: -3.9029

Max Act: 2.6158. Min Act: -0.0001

Data Index: 1115522 (C4 (Web Text))

Max Activating Token Index: 277