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

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

Neuron 4901 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6738. Min Range: -2.6738

Max Act: 2.6738. Min Act: -0.0000

Data Index: 1360370 (Python Code)

Max Activating Token Index: 296

Text #1

Max Range: 2.6738. Min Range: -2.6738

Max Act: 2.6325. Min Act: -0.0000

Data Index: 1499408 (Python Code)

Max Activating Token Index: 808

Text #2

Max Range: 2.6738. Min Range: -2.6738

Max Act: 2.3799. Min Act: -0.0000

Data Index: 1578638 (Python Code)

Max Activating Token Index: 310

Text #3

Max Range: 2.6738. Min Range: -2.6738

Max Act: 2.1808. Min Act: -0.0000

Data Index: 1391737 (Python Code)

Max Activating Token Index: 967

Text #4

Max Range: 2.6738. Min Range: -2.6738

Max Act: 1.9930. Min Act: -0.0000

Data Index: 1428527 (Python Code)

Max Activating Token Index: 810

Text #5

Max Range: 2.6738. Min Range: -2.6738

Max Act: 1.7133. Min Act: -0.0000

Data Index: 1589816 (Python Code)

Max Activating Token Index: 503

Text #6

Max Range: 2.6738. Min Range: -2.6738

Max Act: 1.6273. Min Act: -0.0000

Data Index: 1446639 (Python Code)

Max Activating Token Index: 326

Text #7

Max Range: 2.6738. Min Range: -2.6738

Max Act: 1.7738. Min Act: -0.0000

Data Index: 1365983 (Python Code)

Max Activating Token Index: 810

Text #8

Max Range: 2.6738. Min Range: -2.6738

Max Act: 1.5619. Min Act: -0.0000

Data Index: 1591130 (Python Code)

Max Activating Token Index: 444

Text #9

Max Range: 2.6738. Min Range: -2.6738

Max Act: 1.6029. Min Act: -0.0000

Data Index: 1539636 (Python Code)

Max Activating Token Index: 834

Text #10

Max Range: 2.6738. Min Range: -2.6738

Max Act: 1.6320. Min Act: -0.0000

Data Index: 1623791 (Python Code)

Max Activating Token Index: 536

Text #11

Max Range: 2.6738. Min Range: -2.6738

Max Act: 1.5829. Min Act: -0.0000

Data Index: 1510868 (Python Code)

Max Activating Token Index: 256

Text #12

Max Range: 2.6738. Min Range: -2.6738

Max Act: 1.4393. Min Act: -0.0000

Data Index: 1500557 (Python Code)

Max Activating Token Index: 158

Text #13

Max Range: 2.6738. Min Range: -2.6738

Max Act: 1.5084. Min Act: -0.0000

Data Index: 1619128 (Python Code)

Max Activating Token Index: 736

Text #14

Max Range: 2.6738. Min Range: -2.6738

Max Act: 1.4637. Min Act: -0.0000

Data Index: 1368406 (Python Code)

Max Activating Token Index: 369

Text #15

Max Range: 2.6738. Min Range: -2.6738

Max Act: 1.5340. Min Act: -0.0000

Data Index: 1648071 (Python Code)

Max Activating Token Index: 266

Text #16

Max Range: 2.6738. Min Range: -2.6738

Max Act: 1.4384. Min Act: -0.0000

Data Index: 1422484 (Python Code)

Max Activating Token Index: 276

Text #17

Max Range: 2.6738. Min Range: -2.6738

Max Act: 1.3783. Min Act: -0.0000

Data Index: 1455887 (Python Code)

Max Activating Token Index: 668

Text #18

Max Range: 2.6738. Min Range: -2.6738

Max Act: 1.3431. Min Act: -0.0000

Data Index: 1380938 (Python Code)

Max Activating Token Index: 702

Text #19

Max Range: 2.6738. Min Range: -2.6738

Max Act: 1.3328. Min Act: -0.0000

Data Index: 1470789 (Python Code)

Max Activating Token Index: 566