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

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

Neuron 2249 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.8687. Min Act: -0.0001

Data Index: 1411272 (Python Code)

Max Activating Token Index: 628

Text #1

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6615. Min Act: -0.0001

Data Index: 511108 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6838. Min Act: -0.0001

Data Index: 735842 (C4 (Web Text))

Max Activating Token Index: 475

Text #3

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6107. Min Act: -0.0001

Data Index: 378870 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6529. Min Act: -0.0001

Data Index: 1522380 (Python Code)

Max Activating Token Index: 884

Text #5

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6011. Min Act: -0.0001

Data Index: 546152 (C4 (Web Text))

Max Activating Token Index: 571

Text #6

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6167. Min Act: -0.0001

Data Index: 1511624 (Python Code)

Max Activating Token Index: 145

Text #7

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6251. Min Act: -0.0001

Data Index: 1540322 (Python Code)

Max Activating Token Index: 116

Text #8

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6161. Min Act: -0.0001

Data Index: 17153 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.6108. Min Act: -0.0001

Data Index: 978361 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5684. Min Act: -0.0001

Data Index: 1540125 (Python Code)

Max Activating Token Index: 535

Text #11

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5937. Min Act: -0.0001

Data Index: 1558422 (Python Code)

Max Activating Token Index: 123

Text #12

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5920. Min Act: -0.0001

Data Index: 1534283 (Python Code)

Max Activating Token Index: 9

Text #13

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5478. Min Act: -0.0001

Data Index: 927914 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5568. Min Act: -0.0001

Data Index: 1396912 (Python Code)

Max Activating Token Index: 543

Text #15

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5666. Min Act: -0.0001

Data Index: 1391332 (Python Code)

Max Activating Token Index: 966

Text #16

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5469. Min Act: -0.0001

Data Index: 981083 (C4 (Web Text))

Max Activating Token Index: 297

Text #17

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5685. Min Act: -0.0001

Data Index: 1440904 (Python Code)

Max Activating Token Index: 261

Text #18

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5414. Min Act: -0.0001

Data Index: 1616123 (Python Code)

Max Activating Token Index: 543

Text #19

Max Range: 0.8687. Min Range: -0.8687

Max Act: 0.5575. Min Act: -0.0001

Data Index: 636002 (C4 (Web Text))

Max Activating Token Index: 116