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

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

Neuron 4800 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: 2.2917. Min Range: -2.2917

Max Act: 2.2917. Min Act: -0.0000

Data Index: 1018189 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 2.2917. Min Range: -2.2917

Max Act: 2.1430. Min Act: -0.0000

Data Index: 408483 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 2.2917. Min Range: -2.2917

Max Act: 2.0007. Min Act: -0.0000

Data Index: 923309 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 2.2917. Min Range: -2.2917

Max Act: 1.9807. Min Act: -0.0000

Data Index: 1348440 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 2.2917. Min Range: -2.2917

Max Act: 1.8190. Min Act: -0.0000

Data Index: 1282337 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 2.2917. Min Range: -2.2917

Max Act: 1.7878. Min Act: -0.0000

Data Index: 156403 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 2.2917. Min Range: -2.2917

Max Act: 1.8672. Min Act: -0.0000

Data Index: 149538 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 2.2917. Min Range: -2.2917

Max Act: 1.8432. Min Act: -0.0001

Data Index: 485330 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 2.2917. Min Range: -2.2917

Max Act: 1.8085. Min Act: -0.0000

Data Index: 145258 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 2.2917. Min Range: -2.2917

Max Act: 1.9461. Min Act: -0.0001

Data Index: 926599 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 2.2917. Min Range: -2.2917

Max Act: 1.7702. Min Act: -0.0000

Data Index: 833698 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 2.2917. Min Range: -2.2917

Max Act: 1.5595. Min Act: -0.0000

Data Index: 768361 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 2.2917. Min Range: -2.2917

Max Act: 1.6269. Min Act: -0.0000

Data Index: 570119 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 2.2917. Min Range: -2.2917

Max Act: 1.8286. Min Act: -0.0000

Data Index: 797691 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 2.2917. Min Range: -2.2917

Max Act: 1.6347. Min Act: -0.0001

Data Index: 210785 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 2.2917. Min Range: -2.2917

Max Act: 1.5326. Min Act: -0.0000

Data Index: 418587 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 2.2917. Min Range: -2.2917

Max Act: 1.6408. Min Act: -0.0000

Data Index: 1131932 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 2.2917. Min Range: -2.2917

Max Act: 1.9178. Min Act: -0.0000

Data Index: 313735 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 2.2917. Min Range: -2.2917

Max Act: 1.6331. Min Act: -0.0000

Data Index: 648152 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 2.2917. Min Range: -2.2917

Max Act: 1.5409. Min Act: -0.0001

Data Index: 524804 (C4 (Web Text))

Max Activating Token Index: 62