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

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

Neuron 285 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1568. Min Act: -0.0001

Data Index: 772500 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1588. Min Act: -0.0001

Data Index: 240491 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1391. Min Act: -0.0001

Data Index: 526949 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1600. Min Act: -0.0001

Data Index: 297811 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1426. Min Act: -0.0001

Data Index: 717572 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1444. Min Act: -0.0001

Data Index: 288933 (C4 (Web Text))

Max Activating Token Index: 447

Text #6

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1430. Min Act: -0.0001

Data Index: 966432 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1420. Min Act: -0.0001

Data Index: 852193 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1299. Min Act: -0.0001

Data Index: 378698 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1465. Min Act: -0.0001

Data Index: 363104 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1268. Min Act: -0.0001

Data Index: 452240 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1447. Min Act: -0.0001

Data Index: 526558 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1265. Min Act: -0.0001

Data Index: 224898 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1321. Min Act: -0.0001

Data Index: 501450 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1357. Min Act: -0.0001

Data Index: 355682 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1370. Min Act: -0.0001

Data Index: 1254040 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1306712 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1373. Min Act: -0.0001

Data Index: 206413 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1309. Min Act: -0.0001

Data Index: 708652 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1417. Min Act: -0.0001

Data Index: 1296807 (C4 (Web Text))

Max Activating Token Index: 298