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

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

Neuron 3463 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1078112 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1861. Min Act: -0.0000

Data Index: 421272 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1911. Min Act: -0.0000

Data Index: 1031070 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1836. Min Act: -0.0000

Data Index: 1500867 (Python Code)

Max Activating Token Index: 948

Text #4

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1738. Min Act: -0.0000

Data Index: 708320 (C4 (Web Text))

Max Activating Token Index: 690

Text #5

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1461951 (Python Code)

Max Activating Token Index: 907

Text #6

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1578. Min Act: -0.0000

Data Index: 526845 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1386571 (Python Code)

Max Activating Token Index: 845

Text #8

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1495. Min Act: -0.0000

Data Index: 977051 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1584. Min Act: -0.0000

Data Index: 866189 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1634. Min Act: -0.0000

Data Index: 422301 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1419. Min Act: -0.0000

Data Index: 493147 (C4 (Web Text))

Max Activating Token Index: 975

Text #12

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1467. Min Act: -0.0000

Data Index: 854766 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1455552 (Python Code)

Max Activating Token Index: 433

Text #14

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1611312 (Python Code)

Max Activating Token Index: 527

Text #15

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1405. Min Act: -0.0000

Data Index: 965131 (C4 (Web Text))

Max Activating Token Index: 385

Text #16

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1260. Min Act: -0.0000

Data Index: 1117809 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1378. Min Act: -0.0000

Data Index: 1466699 (Python Code)

Max Activating Token Index: 614

Text #18

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1327. Min Act: -0.0000

Data Index: 1081057 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.1930. Min Range: -0.1930

Max Act: 0.1315. Min Act: -0.0000

Data Index: 1400418 (Python Code)

Max Activating Token Index: 959