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

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

Neuron 1629 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: 0.6620. Min Range: -0.6620

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1215542 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.6444. Min Act: -0.0000

Data Index: 988379 (C4 (Web Text))

Max Activating Token Index: 694

Text #2

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.6490. Min Act: -0.0000

Data Index: 1456197 (Python Code)

Max Activating Token Index: 623

Text #3

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.6283. Min Act: -0.0000

Data Index: 170225 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.6065. Min Act: -0.0000

Data Index: 1230908 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.6123. Min Act: -0.0000

Data Index: 1391002 (Python Code)

Max Activating Token Index: 696

Text #6

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5838. Min Act: -0.0000

Data Index: 1592916 (Python Code)

Max Activating Token Index: 733

Text #7

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5882. Min Act: -0.0000

Data Index: 30499 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5552. Min Act: -0.0000

Data Index: 1359910 (Python Code)

Max Activating Token Index: 910

Text #9

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5439. Min Act: -0.0000

Data Index: 1437060 (Python Code)

Max Activating Token Index: 270

Text #10

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5743. Min Act: -0.0000

Data Index: 1218803 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5770. Min Act: -0.0000

Data Index: 1192330 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5748. Min Act: -0.0000

Data Index: 1598206 (Python Code)

Max Activating Token Index: 590

Text #13

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5830. Min Act: -0.0000

Data Index: 1406550 (Python Code)

Max Activating Token Index: 847

Text #14

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5161. Min Act: -0.0000

Data Index: 1613021 (Python Code)

Max Activating Token Index: 256

Text #15

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5613. Min Act: -0.0000

Data Index: 1552003 (Python Code)

Max Activating Token Index: 872

Text #16

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5423. Min Act: -0.0000

Data Index: 1379511 (Python Code)

Max Activating Token Index: 145

Text #17

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5804. Min Act: -0.0000

Data Index: 1532547 (Python Code)

Max Activating Token Index: 380

Text #18

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5600. Min Act: -0.0000

Data Index: 1418683 (Python Code)

Max Activating Token Index: 520

Text #19

Max Range: 0.6620. Min Range: -0.6620

Max Act: 0.5434. Min Act: -0.0000

Data Index: 959484 (C4 (Web Text))

Max Activating Token Index: 877