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

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

Neuron 4320 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: 2.5476. Min Range: -2.5476

Max Act: 2.5476. Min Act: -0.0000

Data Index: 1457377 (Python Code)

Max Activating Token Index: 973

Text #1

Max Range: 2.5476. Min Range: -2.5476

Max Act: 2.5258. Min Act: -0.0000

Data Index: 1496002 (Python Code)

Max Activating Token Index: 154

Text #2

Max Range: 2.5476. Min Range: -2.5476

Max Act: 2.2674. Min Act: -0.0000

Data Index: 1540093 (Python Code)

Max Activating Token Index: 39

Text #3

Max Range: 2.5476. Min Range: -2.5476

Max Act: 2.2916. Min Act: -0.0000

Data Index: 1485794 (Python Code)

Max Activating Token Index: 914

Text #4

Max Range: 2.5476. Min Range: -2.5476

Max Act: 2.1726. Min Act: -0.0000

Data Index: 1594328 (Python Code)

Max Activating Token Index: 381

Text #5

Max Range: 2.5476. Min Range: -2.5476

Max Act: 2.0430. Min Act: -0.0000

Data Index: 1461624 (Python Code)

Max Activating Token Index: 382

Text #6

Max Range: 2.5476. Min Range: -2.5476

Max Act: 2.1246. Min Act: -0.0000

Data Index: 1594183 (Python Code)

Max Activating Token Index: 44

Text #7

Max Range: 2.5476. Min Range: -2.5476

Max Act: 2.0820. Min Act: -0.0000

Data Index: 1468103 (Python Code)

Max Activating Token Index: 500

Text #8

Max Range: 2.5476. Min Range: -2.5476

Max Act: 2.0799. Min Act: -0.0000

Data Index: 1521457 (Python Code)

Max Activating Token Index: 117

Text #9

Max Range: 2.5476. Min Range: -2.5476

Max Act: 2.0713. Min Act: -0.0000

Data Index: 1364714 (Python Code)

Max Activating Token Index: 413

Text #10

Max Range: 2.5476. Min Range: -2.5476

Max Act: 2.0640. Min Act: -0.0000

Data Index: 1449855 (Python Code)

Max Activating Token Index: 474

Text #11

Max Range: 2.5476. Min Range: -2.5476

Max Act: 1.8819. Min Act: -0.0000

Data Index: 1424684 (Python Code)

Max Activating Token Index: 662

Text #12

Max Range: 2.5476. Min Range: -2.5476

Max Act: 1.9668. Min Act: -0.0000

Data Index: 1535227 (Python Code)

Max Activating Token Index: 389

Text #13

Max Range: 2.5476. Min Range: -2.5476

Max Act: 1.7417. Min Act: -0.0000

Data Index: 1438596 (Python Code)

Max Activating Token Index: 842

Text #14

Max Range: 2.5476. Min Range: -2.5476

Max Act: 1.8311. Min Act: -0.0000

Data Index: 1562746 (Python Code)

Max Activating Token Index: 301

Text #15

Max Range: 2.5476. Min Range: -2.5476

Max Act: 1.8165. Min Act: -0.0000

Data Index: 1583240 (Python Code)

Max Activating Token Index: 409

Text #16

Max Range: 2.5476. Min Range: -2.5476

Max Act: 1.8718. Min Act: -0.0000

Data Index: 1512915 (Python Code)

Max Activating Token Index: 693

Text #17

Max Range: 2.5476. Min Range: -2.5476

Max Act: 1.8702. Min Act: -0.0000

Data Index: 1434579 (Python Code)

Max Activating Token Index: 275

Text #18

Max Range: 2.5476. Min Range: -2.5476

Max Act: 1.8568. Min Act: -0.0000

Data Index: 884853 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 2.5476. Min Range: -2.5476

Max Act: 1.7320. Min Act: -0.0000

Data Index: 1396147 (Python Code)

Max Activating Token Index: 731