Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 433 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1466759 (Python Code)

Max Activating Token Index: 593

Text #1

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1916. Min Act: -0.0000

Data Index: 958760 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1826. Min Act: -0.0000

Data Index: 538606 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1580. Min Act: -0.0001

Data Index: 1582367 (Python Code)

Max Activating Token Index: 370

Text #4

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1524. Min Act: -0.0000

Data Index: 116839 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1606. Min Act: -0.0000

Data Index: 1600230 (Python Code)

Max Activating Token Index: 495

Text #6

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1453. Min Act: -0.0001

Data Index: 1511664 (Python Code)

Max Activating Token Index: 398

Text #7

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1496. Min Act: -0.0000

Data Index: 804734 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1389. Min Act: -0.0001

Data Index: 1373447 (Python Code)

Max Activating Token Index: 310

Text #9

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1415. Min Act: -0.0001

Data Index: 1604737 (Python Code)

Max Activating Token Index: 600

Text #10

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1376. Min Act: -0.0001

Data Index: 1556607 (Python Code)

Max Activating Token Index: 653

Text #11

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1320. Min Act: -0.0000

Data Index: 1627781 (Python Code)

Max Activating Token Index: 913

Text #12

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1196. Min Act: -0.0000

Data Index: 978042 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1314. Min Act: -0.0000

Data Index: 1647192 (Python Code)

Max Activating Token Index: 165

Text #14

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1218. Min Act: -0.0001

Data Index: 1457445 (Python Code)

Max Activating Token Index: 716

Text #15

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1291. Min Act: -0.0001

Data Index: 1590918 (Python Code)

Max Activating Token Index: 231

Text #16

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1237. Min Act: -0.0000

Data Index: 318781 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1196. Min Act: -0.0000

Data Index: 959008 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1217. Min Act: -0.0000

Data Index: 628197 (C4 (Web Text))

Max Activating Token Index: 288

Text #19

Max Range: 0.1932. Min Range: -0.1932

Max Act: 0.1199. Min Act: -0.0001

Data Index: 1452077 (Python Code)

Max Activating Token Index: 813