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

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

Neuron 2730 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2339. Min Range: -1.2339

Max Act: 1.2339. Min Act: -0.0000

Data Index: 219094 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 1.2339. Min Range: -1.2339

Max Act: 1.1540. Min Act: -0.0000

Data Index: 984725 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.9024. Min Act: -0.0000

Data Index: 24978 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.9218. Min Act: -0.0000

Data Index: 589754 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.9182. Min Act: -0.0000

Data Index: 516041 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 1.2339. Min Range: -1.2339

Max Act: 1.0537. Min Act: -0.0000

Data Index: 38049 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.7452. Min Act: -0.0000

Data Index: 104336 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.8473. Min Act: -0.0000

Data Index: 373697 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.8728. Min Act: -0.0000

Data Index: 53785 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.9004. Min Act: -0.0000

Data Index: 1168715 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.9185. Min Act: -0.0000

Data Index: 676164 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1258333 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.7133. Min Act: -0.0000

Data Index: 767298 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.8193. Min Act: -0.0000

Data Index: 163964 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.6949. Min Act: -0.0000

Data Index: 557312 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.6723. Min Act: -0.0000

Data Index: 386392 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.6036. Min Act: -0.0000

Data Index: 224432 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.7332. Min Act: -0.0000

Data Index: 984774 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.5804. Min Act: -0.0000

Data Index: 74974 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.7701. Min Act: -0.0000

Data Index: 342613 (C4 (Web Text))

Max Activating Token Index: 780