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

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

Neuron 784 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: 0.9308. Min Range: -0.9308

Max Act: 0.9308. Min Act: -0.0001

Data Index: 370596 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6558. Min Act: -0.0001

Data Index: 390318 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.8452. Min Act: -0.0001

Data Index: 1041450 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7808. Min Act: -0.0001

Data Index: 720573 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.8152. Min Act: -0.0001

Data Index: 55928 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6224. Min Act: -0.0001

Data Index: 209999 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7875. Min Act: -0.0001

Data Index: 626993 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7450. Min Act: -0.0001

Data Index: 1358243 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7787. Min Act: -0.0001

Data Index: 108953 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7001. Min Act: -0.0001

Data Index: 55332 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7617. Min Act: -0.0001

Data Index: 1176006 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7023. Min Act: -0.0001

Data Index: 583920 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7630. Min Act: -0.0001

Data Index: 526733 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6849. Min Act: -0.0001

Data Index: 1014595 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6626. Min Act: -0.0001

Data Index: 1031533 (C4 (Web Text))

Max Activating Token Index: 679

Text #15

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6651. Min Act: -0.0001

Data Index: 136139 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6741. Min Act: -0.0001

Data Index: 721638 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.7425. Min Act: -0.0001

Data Index: 833886 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6925. Min Act: -0.0001

Data Index: 339044 (C4 (Web Text))

Max Activating Token Index: 503

Text #19

Max Range: 0.9308. Min Range: -0.9308

Max Act: 0.6912. Min Act: -0.0001

Data Index: 766077 (C4 (Web Text))

Max Activating Token Index: 971