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

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

Neuron 1031 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0466. Min Range: -1.0466

Max Act: 1.0466. Min Act: -0.0000

Data Index: 226403 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.8756. Min Act: -0.0000

Data Index: 1103004 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.8668. Min Act: -0.0000

Data Index: 227345 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.6462. Min Act: -0.0000

Data Index: 1050446 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7473. Min Act: -0.0000

Data Index: 60779 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.6203. Min Act: -0.0000

Data Index: 416766 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.6186. Min Act: -0.0000

Data Index: 541897 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.6085. Min Act: -0.0000

Data Index: 275051 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.5642. Min Act: -0.0000

Data Index: 383553 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.5536. Min Act: -0.0000

Data Index: 176781 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.6345. Min Act: -0.0000

Data Index: 367982 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.5107. Min Act: -0.0000

Data Index: 692258 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.5589. Min Act: -0.0000

Data Index: 933697 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.4963. Min Act: -0.0000

Data Index: 583594 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.5143. Min Act: -0.0000

Data Index: 167839 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.3939. Min Act: -0.0000

Data Index: 1283508 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.6358. Min Act: -0.0000

Data Index: 1326293 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.4997. Min Act: -0.0000

Data Index: 721595 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.4756. Min Act: -0.0000

Data Index: 287412 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.5000. Min Act: -0.0000

Data Index: 572311 (C4 (Web Text))

Max Activating Token Index: 979