Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5778 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1949. Min Act: -0.0000

Data Index: 746515 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1440. Min Act: -0.0000

Data Index: 1033029 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1437. Min Act: -0.0000

Data Index: 1285375 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1565. Min Act: -0.0000

Data Index: 275804 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1354. Min Act: -0.0000

Data Index: 1465733 (Python Code)

Max Activating Token Index: 395

Text #5

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1592461 (Python Code)

Max Activating Token Index: 595

Text #6

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1400. Min Act: -0.0000

Data Index: 1564472 (Python Code)

Max Activating Token Index: 635

Text #7

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1441. Min Act: -0.0000

Data Index: 1170593 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1438. Min Act: -0.0000

Data Index: 1550054 (Python Code)

Max Activating Token Index: 331

Text #9

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1484. Min Act: -0.0000

Data Index: 1489356 (Python Code)

Max Activating Token Index: 803

Text #10

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1379. Min Act: -0.0000

Data Index: 1002105 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1310. Min Act: -0.0000

Data Index: 1582905 (Python Code)

Max Activating Token Index: 922

Text #12

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1251. Min Act: -0.0000

Data Index: 555243 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1384. Min Act: -0.0000

Data Index: 1436149 (Python Code)

Max Activating Token Index: 339

Text #14

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1440. Min Act: -0.0000

Data Index: 1397183 (Python Code)

Max Activating Token Index: 768

Text #15

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1198. Min Act: -0.0000

Data Index: 1596448 (Python Code)

Max Activating Token Index: 262

Text #16

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1346298 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1327. Min Act: -0.0000

Data Index: 1586531 (Python Code)

Max Activating Token Index: 240

Text #18

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1332. Min Act: -0.0000

Data Index: 1533837 (Python Code)

Max Activating Token Index: 915

Text #19

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1185780 (C4 (Web Text))

Max Activating Token Index: 962