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

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

Neuron 3923 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: 0.1648. Min Range: -0.1648

Max Act: 0.1648. Min Act: -0.0001

Data Index: 363869 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1470. Min Act: -0.0001

Data Index: 34583 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1562. Min Act: -0.0001

Data Index: 1304418 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1469. Min Act: -0.0001

Data Index: 1108439 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1468. Min Act: -0.0001

Data Index: 125615 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1425. Min Act: -0.0001

Data Index: 310237 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1385. Min Act: -0.0001

Data Index: 925954 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1478. Min Act: -0.0001

Data Index: 498327 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1325. Min Act: -0.0001

Data Index: 1056968 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1285. Min Act: -0.0001

Data Index: 87018 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1378. Min Act: -0.0001

Data Index: 461133 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1312. Min Act: -0.0001

Data Index: 469361 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1267. Min Act: -0.0001

Data Index: 879907 (C4 (Web Text))

Max Activating Token Index: 62

Text #13

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1233. Min Act: -0.0001

Data Index: 1159526 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1281. Min Act: -0.0001

Data Index: 723894 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1315. Min Act: -0.0001

Data Index: 1079504 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1279. Min Act: -0.0001

Data Index: 1086739 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1245. Min Act: -0.0001

Data Index: 3167 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1215. Min Act: -0.0001

Data Index: 546676 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.1648. Min Range: -0.1648

Max Act: 0.1199. Min Act: -0.0001

Data Index: 234659 (C4 (Web Text))

Max Activating Token Index: 91