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

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

Neuron 2563 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: 0.1677. Min Range: -0.1677

Max Act: 0.1677. Min Act: -0.0000

Data Index: 1002706 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1599. Min Act: -0.0000

Data Index: 668151 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1588. Min Act: -0.0001

Data Index: 1167654 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1563. Min Act: -0.0001

Data Index: 1094222 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1538. Min Act: -0.0001

Data Index: 612133 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1502. Min Act: -0.0001

Data Index: 220219 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1434. Min Act: -0.0000

Data Index: 288226 (C4 (Web Text))

Max Activating Token Index: 101

Text #7

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1417. Min Act: -0.0000

Data Index: 407973 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1453. Min Act: -0.0001

Data Index: 831043 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1388. Min Act: -0.0000

Data Index: 1361450 (Python Code)

Max Activating Token Index: 459

Text #10

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1329. Min Act: -0.0001

Data Index: 1177909 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1383. Min Act: -0.0000

Data Index: 102558 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1389. Min Act: -0.0001

Data Index: 711579 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1294. Min Act: -0.0000

Data Index: 332405 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1288. Min Act: -0.0000

Data Index: 285446 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1475. Min Act: -0.0000

Data Index: 158496 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1328. Min Act: -0.0001

Data Index: 773921 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1351. Min Act: -0.0001

Data Index: 391647 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1147478 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1336. Min Act: -0.0001

Data Index: 1064224 (C4 (Web Text))

Max Activating Token Index: 467