Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3144 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2260. Min Range: -2.2260

Max Act: 2.2260. Min Act: -0.0000

Data Index: 602169 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 2.2260. Min Range: -2.2260

Max Act: 2.0599. Min Act: -0.0000

Data Index: 758716 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 2.2260. Min Range: -2.2260

Max Act: 1.7263. Min Act: -0.0000

Data Index: 466780 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 2.2260. Min Range: -2.2260

Max Act: 1.8078. Min Act: -0.0000

Data Index: 603154 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 2.2260. Min Range: -2.2260

Max Act: 1.7691. Min Act: -0.0000

Data Index: 1003754 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 2.2260. Min Range: -2.2260

Max Act: 1.6229. Min Act: -0.0000

Data Index: 572208 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 2.2260. Min Range: -2.2260

Max Act: 1.6430. Min Act: -0.0000

Data Index: 922577 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 2.2260. Min Range: -2.2260

Max Act: 1.6287. Min Act: -0.0000

Data Index: 72080 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 2.2260. Min Range: -2.2260

Max Act: 1.5391. Min Act: -0.0000

Data Index: 1018398 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 2.2260. Min Range: -2.2260

Max Act: 1.5526. Min Act: -0.0000

Data Index: 454430 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 2.2260. Min Range: -2.2260

Max Act: 1.4291. Min Act: -0.0001

Data Index: 522135 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 2.2260. Min Range: -2.2260

Max Act: 1.5124. Min Act: -0.0001

Data Index: 444091 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 2.2260. Min Range: -2.2260

Max Act: 1.4089. Min Act: -0.0000

Data Index: 1251571 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 2.2260. Min Range: -2.2260

Max Act: 1.4547. Min Act: -0.0000

Data Index: 174734 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 2.2260. Min Range: -2.2260

Max Act: 1.4827. Min Act: -0.0001

Data Index: 41508 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 2.2260. Min Range: -2.2260

Max Act: 1.4566. Min Act: -0.0000

Data Index: 467980 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 2.2260. Min Range: -2.2260

Max Act: 1.3853. Min Act: -0.0001

Data Index: 716334 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 2.2260. Min Range: -2.2260

Max Act: 1.3454. Min Act: -0.0001

Data Index: 1127677 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 2.2260. Min Range: -2.2260

Max Act: 1.4070. Min Act: -0.0001

Data Index: 162966 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 2.2260. Min Range: -2.2260

Max Act: 1.3928. Min Act: -0.0001

Data Index: 378983 (C4 (Web Text))

Max Activating Token Index: 246