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

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

Neuron 1877 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1826. Min Act: -0.0000

Data Index: 731530 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1867. Min Act: -0.0000

Data Index: 720759 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1583. Min Act: -0.0001

Data Index: 896916 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1639. Min Act: -0.0000

Data Index: 291814 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1558. Min Act: -0.0000

Data Index: 664899 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1547. Min Act: -0.0000

Data Index: 894385 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1591. Min Act: -0.0000

Data Index: 558130 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1573. Min Act: -0.0000

Data Index: 329270 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1621. Min Act: -0.0000

Data Index: 505390 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1472. Min Act: -0.0000

Data Index: 734844 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1351. Min Act: -0.0000

Data Index: 351278 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1359. Min Act: -0.0000

Data Index: 763798 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1304. Min Act: -0.0000

Data Index: 600796 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1298. Min Act: -0.0000

Data Index: 474151 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1286. Min Act: -0.0000

Data Index: 1313888 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1308. Min Act: -0.0000

Data Index: 1288282 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1350430 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1368. Min Act: -0.0000

Data Index: 1343871 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1266. Min Act: -0.0000

Data Index: 77624 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 0.1867. Min Range: -0.1867

Max Act: 0.1176. Min Act: -0.0000

Data Index: 425427 (C4 (Web Text))

Max Activating Token Index: 896