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

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

Neuron 5794 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6561. Min Range: -1.6561

Max Act: 1.6561. Min Act: -0.0000

Data Index: 1346281 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 1.6561. Min Range: -1.6561

Max Act: 1.5173. Min Act: -0.0000

Data Index: 1054050 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 1.6561. Min Range: -1.6561

Max Act: 1.3194. Min Act: -0.0000

Data Index: 1580068 (Python Code)

Max Activating Token Index: 512

Text #3

Max Range: 1.6561. Min Range: -1.6561

Max Act: 1.2364. Min Act: -0.0000

Data Index: 1636503 (Python Code)

Max Activating Token Index: 1010

Text #4

Max Range: 1.6561. Min Range: -1.6561

Max Act: 1.2615. Min Act: -0.0000

Data Index: 1572506 (Python Code)

Max Activating Token Index: 398

Text #5

Max Range: 1.6561. Min Range: -1.6561

Max Act: 1.2335. Min Act: -0.0000

Data Index: 1294042 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 1.6561. Min Range: -1.6561

Max Act: 1.1102. Min Act: -0.0000

Data Index: 1046666 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 1.6561. Min Range: -1.6561

Max Act: 1.1715. Min Act: -0.0000

Data Index: 341413 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 1.6561. Min Range: -1.6561

Max Act: 1.1510. Min Act: -0.0000

Data Index: 1025931 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 1.6561. Min Range: -1.6561

Max Act: 1.1472. Min Act: -0.0000

Data Index: 1549760 (Python Code)

Max Activating Token Index: 775

Text #10

Max Range: 1.6561. Min Range: -1.6561

Max Act: 1.1108. Min Act: -0.0000

Data Index: 726271 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 1.6561. Min Range: -1.6561

Max Act: 1.0318. Min Act: -0.0000

Data Index: 204770 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 1.6561. Min Range: -1.6561

Max Act: 0.9363. Min Act: -0.0000

Data Index: 363913 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 1.6561. Min Range: -1.6561

Max Act: 1.0694. Min Act: -0.0000

Data Index: 1522728 (Python Code)

Max Activating Token Index: 109

Text #14

Max Range: 1.6561. Min Range: -1.6561

Max Act: 0.9795. Min Act: -0.0000

Data Index: 1019513 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 1.6561. Min Range: -1.6561

Max Act: 0.9545. Min Act: -0.0000

Data Index: 1171674 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 1.6561. Min Range: -1.6561

Max Act: 0.9671. Min Act: -0.0000

Data Index: 95381 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 1.6561. Min Range: -1.6561

Max Act: 0.9504. Min Act: -0.0000

Data Index: 510270 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 1.6561. Min Range: -1.6561

Max Act: 0.9167. Min Act: -0.0000

Data Index: 1491089 (Python Code)

Max Activating Token Index: 928

Text #19

Max Range: 1.6561. Min Range: -1.6561

Max Act: 0.9173. Min Act: -0.0000

Data Index: 907513 (C4 (Web Text))

Max Activating Token Index: 977