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

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

Neuron 2928 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: 0.1742. Min Range: -0.1742

Max Act: 0.1687. Min Act: -0.0001

Data Index: 1291373 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1742. Min Act: -0.0001

Data Index: 482262 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1395. Min Act: -0.0001

Data Index: 1260653 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1430. Min Act: -0.0001

Data Index: 1129004 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1409. Min Act: -0.0001

Data Index: 395007 (C4 (Web Text))

Max Activating Token Index: 233

Text #5

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1387. Min Act: -0.0001

Data Index: 431257 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1390. Min Act: -0.0001

Data Index: 627306 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1429. Min Act: -0.0001

Data Index: 1134328 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1372. Min Act: -0.0001

Data Index: 622696 (C4 (Web Text))

Max Activating Token Index: 578

Text #9

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1418. Min Act: -0.0001

Data Index: 849565 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1361. Min Act: -0.0001

Data Index: 459004 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1392. Min Act: -0.0001

Data Index: 1180405 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1310. Min Act: -0.0001

Data Index: 1088355 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1398. Min Act: -0.0001

Data Index: 1235392 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1342. Min Act: -0.0001

Data Index: 696787 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1327. Min Act: -0.0001

Data Index: 110961 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1375. Min Act: -0.0001

Data Index: 1259838 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1311. Min Act: -0.0001

Data Index: 945843 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1241. Min Act: -0.0001

Data Index: 763738 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1233. Min Act: -0.0001

Data Index: 581850 (C4 (Web Text))

Max Activating Token Index: 252