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

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

Neuron 2348 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: 0.9383. Min Range: -0.9383

Max Act: 0.8724. Min Act: -0.0000

Data Index: 1095562 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8460. Min Act: -0.0000

Data Index: 982479 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.9113. Min Act: -0.0000

Data Index: 1293363 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8014. Min Act: -0.0000

Data Index: 872751 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8078. Min Act: -0.0000

Data Index: 760104 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8290. Min Act: -0.0000

Data Index: 25825 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.9383. Min Act: -0.0000

Data Index: 1059935 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.8437. Min Act: -0.0000

Data Index: 909901 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7501. Min Act: -0.0000

Data Index: 729154 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7255. Min Act: -0.0000

Data Index: 55794 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7245. Min Act: -0.0000

Data Index: 1165343 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7604. Min Act: -0.0000

Data Index: 686411 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7421. Min Act: -0.0000

Data Index: 887586 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7100. Min Act: -0.0000

Data Index: 977201 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7394. Min Act: -0.0000

Data Index: 240979 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.6709. Min Act: -0.0000

Data Index: 480694 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.5787. Min Act: -0.0000

Data Index: 250843 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.7200. Min Act: -0.0000

Data Index: 908319 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.6412. Min Act: -0.0000

Data Index: 860996 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 0.9383. Min Range: -0.9383

Max Act: 0.6584. Min Act: -0.0000

Data Index: 1173605 (C4 (Web Text))

Max Activating Token Index: 948